© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101414
    Prev
    Next
    INDEX
    Explanations

    locations and places

    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_10/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
     and
    -2.36
     suscripción
    -2.06
     instalação
    -1.96
    otry
    -1.95
    >
    -1.93
    wwwww
    -1.91
     Meilleures
    -1.88
     eenvou
    -1.84
     bekende
    -1.82
     skool
    -1.81
    POSITIVE LOGITS
    p
    2.50
    ma
    2.25
    d
    2.17
    c
    2.14
    甚至是
    2.03
    al
    2.02
    n
    2.02
     kunnen
    1.97
    ating
    1.92
     totals
    1.88
    Activations Density 0.005%

    No Known Activations