© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181692
    Prev
    Next
    INDEX
    Explanations

    link below or beneath

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

    distinction or classification details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    歇
    0.50
    لې
    0.47
    废
    0.47
    过期
    0.46
    沒
    0.45
    Versions
    0.45
    程度上
    0.45
     effekt
    0.45
    氣
    0.45
    ម្លៃ
    0.44
    POSITIVE LOGITS
     же
    0.48
    %$
    0.48
    uff
    0.47
    uras
    0.47
     کند
    0.46
    Ι
    0.46
     явля
    0.44
     зобра
    0.44
     gráfico
    0.43
     έναν
    0.43
    Activations Density 0.001%

    No Known Activations