© 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. 8830
    Prev
    Next
    INDEX
    Explanations

    method calls 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
    に対する
    -1.45
     Anſ
    -1.42
     Dinas
    -1.42
    taya
    -1.39
     pary
    -1.38
     ſont
    -1.38
    ledad
    -1.34
     spesso
    -1.34
    derdag
    -1.33
     unſ
    -1.32
    POSITIVE LOGITS
     any
    3.19
     when
    2.11
     in
    1.93
     or
    1.84
     if
    1.77
     this
    1.72
     anything
    1.68
     at
    1.55
    任何
    1.54
     even
    1.50
    Activations Density 0.052%

    No Known Activations