© 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. 182799
    Prev
    Next
    INDEX
    Explanations

    anticipating usage, database contacts

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

    `reduce()` method

    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
    iras
    0.52
     lea
    0.50
     לח
    0.49
    put
    0.49
    ?
    0.46
    into
    0.44
    חד
    0.44
    ዋ
    0.44
     direc
    0.44
     усили
    0.43
    POSITIVE LOGITS
    𝐑
    0.47
     Taunton
    0.45
     Jeux
    0.45
     ESTATE
    0.45
     colours
    0.45
    湇
    0.45
    ിൽ
    0.44
     ಮತ್ತು
    0.44
    唃
    0.44
     égaux
    0.44
    Activations Density 0.000%

    No Known Activations