© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63989
    Prev
    Next
    INDEX
    Explanations

    http-equiv content="text/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fitter
    -0.65
    てる
    -0.65
    mickey
    -0.63
    channelId
    -0.63
    Donor
    -0.63
    stanley
    -0.63
    Qn
    -0.62
     dera
    -0.62
    contributor
    -0.62
    oq
    -0.60
    POSITIVE LOGITS
    toBe
    0.82
     JV
    0.79
     atrap
    0.79
    нева
    0.75
     Wär
    0.75
     DMCA
    0.73
    (/\
    0.72
    🕑
    0.72
    questions
    0.72
    ductors
    0.71
    Activations Density 0.038%

    No Known Activations