© 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. 10-GEMMASCOPE-RES-131K
    7. 68242
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    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
    _
    -1.88
    瓩
    -1.76
    ns
    -1.73
     are
    -1.69
     Its
    -1.69
    and
    -1.68
     notwendigen
    -1.65
     Here
    -1.63
    part
    -1.63
    ow
    -1.61
    POSITIVE LOGITS
    emény
    1.69
    Étymologie
    1.56
     documental
    1.56
     dij
    1.55
     grup
    1.53
     jotka
    1.52
    🥈
    1.52
     玄関
    1.51
    ࿙
    1.49
    colgante
    1.47
    Activations Density 0.007%

    No Known Activations