© 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. 102124
    Prev
    Next
    INDEX
    Explanations

    credits, legal, or conditional statements

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

    SQL SELECT statements

    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
    ﾗ
    0.49
    お店
    0.47
    Batter
    0.45
    琹
    0.45
     дос
    0.44
    ִ
    0.44
    絟
    0.44
     ежедневно
    0.43
    ριν
    0.43
    りん
    0.43
    POSITIVE LOGITS
     +\
    0.50
     that
    0.49
     which
    0.49
     Ngh
    0.48
     +
    0.47
     when
    0.47
     AD
    0.47
    +\
    0.47
     an
    0.46
     -\
    0.45
    Activations Density 0.004%

    No Known Activations