© 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. 33508
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    date separator

    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
     seventh
    0.44
     businessman
    0.44
    مين
    0.42
    م
    0.42
    сев
    0.41
     company
    0.41
    good
    0.41
     wann
    0.41
    のことを
    0.41
     businessmen
    0.40
    POSITIVE LOGITS
    igating
    0.50
    ্ষিক
    0.50
    🐊
    0.46
    elevationMap
    0.46
     μορ
    0.46
    दर्शिता
    0.45
    idł
    0.44
    🖼
    0.44
    umably
    0.44
    osomal
    0.43
    Activations Density 0.011%

    No Known Activations