© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8434
    Prev
    Next
    INDEX
    Explanations

    department of

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

    This neuron fires on tokens that introduce or label new informational sections or details—e.g. administrative divisions (“department”), spatial cues (“below”), amenities (“bathroom,” “relax”), or conditional qualifiers (“depending”).

    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
    -
    0.93
    _
    0.84
     R
    0.82
    et
    0.81
     men
    0.80
    n
    0.80
    t
    0.79
     X
    0.77
     set
    0.77
    /
    0.77
    POSITIVE LOGITS
    <unused94>
    0.98
    ಶ್ರೀ
    0.96
    게요
    0.92
     fudai
    0.91
    先日
    0.90
    ポケモン
    0.89
     faptul
    0.89
    ␊
    0.89
    まずは
    0.88
    ❓
    0.88
    Activations Density 0.000%

    No Known Activations