© 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. 238421
    Prev
    Next
    INDEX
    Explanations

    latest round

    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
    衄
    0.57
    秚
    0.55
    मुख
    0.54
    崠
    0.53
    浾
    0.53
    稦
    0.53
    佲
    0.52
    遒
    0.52
    鏗
    0.52
     หม
    0.51
    POSITIVE LOGITS
    :
    0.54
    on
    0.46
     developer
    0.46
     as
    0.46
    <b>
    0.45
    heses
    0.45
     developers
    0.43
    <strong>
    0.43
    co
    0.43
    ベ
    0.43
    Activations Density 0.000%

    No Known Activations