© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 457
    Prev
    Next
    INDEX
    Explanations

    trusted love

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron consistently lights up on second-person pronouns and imperative constructions (e.g. “you,” “your,” “need to”), i.e. when the text addresses the reader directly.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    second-person pronouns ("you") in instructional or persuasive text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    second-person, promotional or instructional web copy with an advertorial/SEO-spam tone that gives generic advice and calls to action.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.28
     and
    0.26
     or
    0.25
    h
    0.24
     please
    0.24
     
    0.24
    ...
    0.23
    _
    0.23
     song
    0.23
     b
    0.22
    POSITIVE LOGITS
     Hesap
    0.28
     Zusätzlich
    0.28
    <unused355>
    0.28
    sächlich
    0.28
     Faktoren
    0.27
    <unused339>
    0.27
    ྪ
    0.26
     Meskipun
    0.26
     Özellikle
    0.26
     Они
    0.26
    Activations Density 0.594%

    No Known Activations