© 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. 22-GEMMASCOPE-RES-131K
    7. 26762
    Prev
    Next
    INDEX
    Explanations

    interface/generic type extension

    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
     during
    -1.39
     by
    -1.39
     had
    -1.25
     it
    -1.24
    šanas
    -1.23
     because
    -1.23
     years
    -1.21
    huevos
    -1.20
     first
    -1.17
    Bibliografie
    -1.17
    POSITIVE LOGITS
    ftal
    1.25
    having
    1.24
    ;'
    1.23
     solamente
    1.23
    ΄
    1.20
    好像
    1.20
    
    1.20
    所有
    1.19
     ángulo
    1.18
     apenas
    1.17
    Activations Density 0.018%

    No Known Activations