© 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. 7419
    Prev
    Next
    INDEX
    Explanations

    local variable and function declarations

    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
    -1.87
    ”،
    -1.77
     as
    -1.76
     will
    -1.75
     on
    -1.71
     for
    -1.70
     is
    -1.67
     had
    -1.64
    It
    -1.62
     with
    -1.60
    POSITIVE LOGITS
    皝
    1.72
     régal
    1.66
    certainly
    1.63
     peux
    1.59
     willen
    1.59
     véhic
    1.55
    PÁG
    1.55
    actually
    1.55
     commencent
    1.53
     refroid
    1.48
    Activations Density 0.007%

    No Known Activations