© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    programming tokens, code syntax

    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
     even
    -1.85
    ↵↵
    -1.59
     at
    -1.58
     all
    -1.41
    MathML
    -1.38
     not
    -1.34
    蘊
    -1.30
    <tr>
    -1.29
    u
    -1.22
    ssons
    -1.18
    POSITIVE LOGITS
     bekämp
    1.63
     ponieważ
    1.45
     katkı
    1.38
    wortet
    1.34
    ває
    1.34
    さすが
    1.32
     écout
    1.27
    
    1.26
     novos
    1.26
    たぶん
    1.24
    Activations Density 0.059%

    No Known Activations