© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 396
    Prev
    Next
    INDEX
    Explanations

    a specific action or state

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

    This neuron responds to formal, academic‐style prose—that is, technical or scholarly writing.

    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_31_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
     bạn
    0.45
    0.40
    اا
    0.36
    I
    0.36
    2
    0.35
    K
    0.34
     tốt
    0.34
    v
    0.34
    D
    0.33
    d
    0.33
    POSITIVE LOGITS
     proletariat
    0.46
     prolet
    0.40
     bourgeoisie
    0.37
    <unused1733>
    0.37
     diminution
    0.35
    <unused534>
    0.35
     pulsation
    0.35
     coscienza
    0.34
     bourgeois
    0.34
     antagonism
    0.34
    Activations Density 0.224%

    No Known Activations