© 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. 73099
    Prev
    Next
    INDEX
    Explanations

    header includes

    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
    '
    -1.93
     our
    -1.86
    providedIn
    -1.63
    𓐍
    -1.59
    -
    -1.59
     печи
    -1.55
    了很多
    -1.53
    इटम
    -1.50
    -1.49
    唠
    -1.48
    POSITIVE LOGITS
     シルエット
    1.53
    
    1.51
     but
    1.49
     suoi
    1.49
     tetapi
    1.46
     ему
    1.45
    他
    1.45
     carrot
    1.41
    ↵↵
    1.39
     cependant
    1.38
    Activations Density 0.029%

    No Known Activations