© 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. 6287
    Prev
    Next
    INDEX
    Explanations

    at the

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

    This neuron spotlights mentions of specific titled works (e.g. the names of paintings or books).

    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
    blas
    0.59
     zusamm
    0.59
    Ⴖ
    0.59
     краса
    0.58
     przedsi
    0.57
    hatu
    0.56
     साझे
    0.56
    સભા
    0.56
     девушка
    0.54
     vuurp
    0.53
    POSITIVE LOGITS
     mo
    0.55
     sacs
    0.55
     potem
    0.54
     moot
    0.52
    ொ
    0.52
     Frem
    0.50
     bearer
    0.50
     cặp
    0.50
    ضغط
    0.50
    货
    0.50
    Activations Density 0.000%

    No Known Activations