© 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. 36517
    Prev
    Next
    INDEX
    Explanations

    authorize to settle

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

    choice of politeness/theft/legal

    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
    க்கிறது
    0.45
    鍘
    0.45
    ASSOCI
    0.43
    刄
    0.42
    രാജ
    0.40
    тат
    0.39
    )");
    0.39
    احمد
    0.39
    高
    0.39
     Astronomy
    0.38
    POSITIVE LOGITS
    citizen
    0.45
    pract
    0.45
    čiai
    0.45
    rea
    0.44
    bow
    0.44
    ség
    0.43
    adie
    0.42
    peut
    0.42
    how
    0.42
    いが
    0.42
    Activations Density 0.001%

    No Known Activations