© 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. 15243
    Prev
    Next
    INDEX
    Explanations

    Av, btw

    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
    犼
    -3.38
     yf
    -3.19
    螄
    -3.17
     内衣
    -3.13
     复古
    -3.05
    珰
    -3.03
     nini
    -3.00
     插图
    -2.97
     排骨
    -2.95
    涠
    -2.95
    POSITIVE LOGITS
     Commonly
    3.78
    2
    3.63
     Occasionally
    3.52
     Currently
    3.48
    To
    3.41
    5
    3.20
     soothe
    3.20
     Personally
    3.13
     Approximately
    3.09
     Then
    3.06
    Activations Density 0.002%

    No Known Activations