© 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. 111469
    Prev
    Next
    INDEX
    Explanations

    one such

    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
    茕
    -2.08
     hvis
    -2.08
     أجل
    -2.06
    艫
    -2.06
     flere
    -2.06
     quí
    -1.99
     følgende
    -1.98
    猡
    -1.97
     begge
    -1.95
    ︲
    -1.95
    POSITIVE LOGITS
     in
    2.31
     —
    2.03
     unangemessene
    1.96
     standout
    1.95
     I
    1.93
     \"
    1.85
     like
    1.84
     However
    1.77
    l
    1.76
     expedite
    1.74
    Activations Density 0.006%

    No Known Activations