© 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. 8296
    Prev
    Next
    INDEX
    Explanations

    is it possible to

    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
    umerable
    -1.58
     ส์
    -1.58
    "}";
    -1.58
    ">(</
    -1.52
    でも
    -1.52
     используют
    -1.52
     molti
    -1.48
     havde
    -1.48
     distinctive
    -1.46
    igth
    -1.46
    POSITIVE LOGITS
     other
    1.80
     Despite
    1.73
     could
    1.65
     Because
    1.59
     really
    1.55
     After
    1.53
    他已经
    1.48
     would
    1.47
     While
    1.44
     help
    1.43
    Activations Density 0.106%

    No Known Activations