© 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. 8559
    Prev
    Next
    INDEX
    Explanations

    actions, information, energy

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

    The neuron fires strongly on second-person pronouns and their common auxiliaries (e.g. “you,” “have,” “are”)—marking direct address to the reader.

    oai_token-act-pair · o4-miniTriggered 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
    𝓱
    0.80
    际
    0.77
    ル
    0.77
    ensation
    0.77
    <0x98>
    0.76
     n
    0.76
     н
    0.76
    נ
    0.76
    क्र
    0.75
    𝐧
    0.75
    POSITIVE LOGITS
    farande
    0.83
    ai
    0.80
     servings
    0.79
     hintergrund
    0.79
    emis
    0.77
    azuje
    0.77
    niches
    0.76
    jenigen
    0.74
    knings
    0.74
     mikt
    0.74
    Activations Density 0.002%

    No Known Activations