© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    was born or posted

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

    code, punctuation, and symbols

    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
    }$&$-
    0.33
    resultado
    0.32
    kirche
    0.31
     chwil
    0.30
     logarith
    0.30
    yemek
    0.30
    𒍣
    0.29
     ferrug
    0.29
     encontra
    0.29
     mancanza
    0.29
    POSITIVE LOGITS
     {
    0.41
     ("
    0.39
     ('
    0.36
     />
    0.35
     (“
    0.34
     TODO
    0.34
    Ｉ
    0.34
    ">
    0.33
    <0xE3>
    0.33
     {/*
    0.32
    Activations Density 0.110%

    No Known Activations