© 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. 12889
    Prev
    Next
    INDEX
    Explanations

    closing parentheses

    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
    $
    -3.95
    .
    -3.16
    One
    -3.14
    I
    -3.08
    Only
    -2.97
    肫
    -2.92
    L
    -2.78
    Our
    -2.66
    For
    -2.66
    No
    -2.64
    POSITIVE LOGITS
    髕
    3.19
     we
    2.98
     queridos
    2.72
    Ɑ
    2.55
    
    2.48
     diarios
    2.47
     favoritos
    2.44
     conocidas
    2.44
     are
    2.42
     který
    2.42
    Activations Density 0.008%

    No Known Activations