© 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. 78277
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
     seventies
    -0.91
     Janata
    -0.72
    rink
    -0.72
    veto
    -0.70
    bateria
    -0.69
     ADO
    -0.69
    mechanic
    -0.69
     Mannes
    -0.68
    水瓶
    -0.68
     bral
    -0.68
    POSITIVE LOGITS
     Boko
    0.93
     blog
    0.77
    chdir
    0.76
    vese
    0.76
     Zukunft
    0.75
     deems
    0.73
    网站
    0.72
    ∈
    0.70
    eably
    0.70
     blogger
    0.69
    Activations Density 0.080%

    No Known Activations