© 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. 129517
    Prev
    Next
    INDEX
    Explanations

    states paired with

    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
     also
    -2.11
     That
    -1.80
     was
    -1.73
     with
    -1.72
     convirtió
    -1.71
     according
    -1.70
    enerbah
    -1.67
    ussure
    -1.60
     already
    -1.58
    :
    -1.55
    POSITIVE LOGITS
    ing
    1.81
     manier
    1.73
    standing
    1.73
    ely
    1.66
    hing
    1.64
    stand
    1.63
    VILLE
    1.62
    чним
    1.62
    ments
    1.60
    ards
    1.59
    Activations Density 0.010%

    No Known Activations