© 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. 113314
    Prev
    Next
    INDEX
    Explanations

    restricted amid

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

    gain legitimate access or variables

    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
    𝔀
    0.52
    َى
    0.50
    iserum
    0.48
    雓
    0.48
     коэффициент
    0.48
    ších
    0.46
    pieceSelection
    0.46
     संगम
    0.46
    ܸ
    0.46
     入っ
    0.46
    POSITIVE LOGITS
    <b>
    0.49
     expense
    0.47
     mold
    0.46
     Harv
    0.46
     formats
    0.46
    l
    0.45
     author
    0.45
     “
    0.45
     lex
    0.45
    デジタル
    0.44
    Activations Density 0.001%

    No Known Activations