© 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. 25394
    Prev
    Next
    INDEX
    Explanations

    after `reasonable`, `window`, `cache`, `of`

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

    Destination Zone, Hidden Layer, Spinal Cord, Head of

    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
     जिनका
    0.43
    eraj
    0.41
    t
    0.41
    ozat
    0.39
    ﾀ
    0.39
    að
    0.38
    foration
    0.38
    them
    0.38
    max
    0.37
    altura
    0.37
    POSITIVE LOGITS
     enzim
    0.38
     enfer
    0.37
     restor
    0.37
     سمع
    0.37
     posts
    0.36
    ەن
    0.36
     malu
    0.36
    %%%%%%%%%%%%
    0.35
     mencegah
    0.35
    やお
    0.35
    Activations Density 0.000%

    No Known Activations