© 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. 128350
    Prev
    Next
    INDEX
    Explanations

    clarifying definitions

    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
     by
    -1.96
     in
    -1.91
     didn
    -1.66
     had
    -1.64
    in
    -1.61
    M
    -1.55
    T
    -1.53
     was
    -1.52
     have
    -1.52
    B
    -1.51
    POSITIVE LOGITS
    Santé
    1.48
     auront
    1.46
    рија
    1.43
    Mijn
    1.41
     iemand
    1.40
     rése
    1.39
     spreken
    1.38
    嵓
    1.38
    Réalisation
    1.38
     mystérie
    1.37
    Activations Density 0.200%

    No Known Activations