© 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. 22-GEMMASCOPE-RES-131K
    7. 130258
    Prev
    Next
    INDEX
    Explanations

    code library programming

    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_22/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
    페
    -1.02
     Of
    -0.94
    攞
    -0.93
    ：【
    -0.90
    )):
    -0.84
     "",
    -0.83
    抜粋
    -0.82
    GEO
    -0.82
    Чтоб
    -0.81
    一點
    -0.80
    POSITIVE LOGITS
     natuurlijke
    1.11
    

    1.02
     różnych
    0.96
    CCIÓN
    0.88
    StackNavigator
    0.86
     trợ
    0.86
     verantwoorde
    0.86
     verschillende
    0.86
    ARDI
    0.86
    διά
    0.85
    Activations Density 0.082%

    No Known Activations