© 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. 190437
    Prev
    Next
    INDEX
    Explanations

    facility for

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

    how to answer questions

    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
     ресто
    0.45
    ନ
    0.45
    нное
    0.44
    藏
    0.44
    вно
    0.43
    フォー
    0.43
    X
    0.42
    婊
    0.42
     участ
    0.42
    น
    0.42
    POSITIVE LOGITS
     sucr
    0.46
     buses
    0.46
    اي
    0.45
     pleaded
    0.45
     transporters
    0.44
     गर्
    0.44
     manipulator
    0.44
     eneste
    0.44
     forhold
    0.43
     nub
    0.43
    Activations Density 0.000%

    No Known Activations