© 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. 74135
    Prev
    Next
    INDEX
    Explanations

    topics/technical terms

    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
     effici
    -1.80
     procédures
    -1.59
     prochaines
    -1.55
     ridu
    -1.52
     coûts
    -1.50
     délais
    -1.49
     batte
    -1.48
     メニュー
    -1.47
     soto
    -1.47
     besoins
    -1.46
    POSITIVE LOGITS
     time
    1.95
     J
    1.77
     people
    1.70
     \&
    1.65
     H
    1.63
     at
    1.62
     experiences
    1.59
     K
    1.58
     various
    1.56
     p
    1.55
    Activations Density 0.153%

    No Known Activations