© 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. 13918
    Prev
    Next
    INDEX
    Explanations

    citations like [^1]

    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
     any
    -1.79
     our
    -1.77
     them
    -1.67
     said
    -1.66
     but
    -1.62
     which
    -1.54
     an
    -1.43
     the
    -1.42
     Our
    -1.41
     whom
    -1.41
    POSITIVE LOGITS
     его
    1.74
     этой
    1.67
    씰
    1.66
     этих
    1.66
    地说道
    1.62
     ocultar
    1.62
    👎
    1.60
     Accueil
    1.59
     Réponses
    1.58
     Ubicación
    1.58
    Activations Density 0.008%

    No Known Activations