© 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. 71076
    Prev
    Next
    INDEX
    Explanations

    code or 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
     =
    -1.60
    0
    -1.52
    Its
    -1.52
    -
    -1.52
     ansatte
    -1.52
    一旁的
    -1.48
    ations
    -1.48
     "
    -1.47
    жды
    -1.46
     hjemmes
    -1.45
    POSITIVE LOGITS
     not
    2.28
     that
    2.13
     of
    1.91
     notare
    1.70
     have
    1.67
    %;
    1.62
     which
    1.62
     mostrare
    1.58
    Ꮟ
    1.56
     wła
    1.55
    Activations Density 0.001%

    No Known Activations