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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12518
    Prev
    Next
    INDEX
    Explanations

    article

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

    The neuron strongly responds to asterisk characters used as list or bullet markers.

    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
    MOUSE
    0.58
     *=
    0.57
    JAK
    0.56
    cream
    0.56
    Myers
    0.55
    APDS
    0.55
     மூ
    0.54
     ış
    0.54
     Wiss
    0.54
    APA
    0.53
    POSITIVE LOGITS
     samego
    0.54
     статью
    0.53
     saker
    0.53
    astly
    0.53
     zain
    0.53
    ﻕ
    0.52
    一張
    0.52
     статья
    0.52
    ంటి
    0.51
     Danube
    0.51
    Activations Density 0.000%

    No Known Activations