© 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. 67720
    Prev
    Next
    INDEX
    Explanations

    view/views/controllers/pages

    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
     not
    -1.92
     usually
    -1.73
     often
    -1.73
     also
    -1.66
     be
    -1.59
    k
    -1.55
     always
    -1.53
     aforementioned
    -1.52
     first
    -1.51
     continued
    -1.49
    POSITIVE LOGITS
     Antwerpen
    1.63
     taal
    1.63
    隨著
    1.55
     Maak
    1.52
     absolut
    1.50
    如果
    1.49
     ſta
    1.49
    随着
    1.48
     Godt
    1.48
    Doesn
    1.46
    Activations Density 0.001%

    No Known Activations