© 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. 84052
    Prev
    Next
    INDEX
    Explanations

    customer service, trust relationships, fuel resources

    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
     from
    -2.56
     in
    -2.28
     after
    -2.13
     because
    -1.92
     intricate
    -1.88
    because
    -1.82
     since
    -1.79
     these
    -1.73
    ."
    -1.60
    Nearly
    -1.56
    POSITIVE LOGITS
     is
    1.64
    izate
    1.58
     alcune
    1.57
    atical
    1.52
     iy
    1.49
     bè
    1.49
    鲠
    1.46
     zoude
    1.44
     gâ
    1.44
     tâ
    1.42
    Activations Density 0.244%

    No Known Activations