© 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. 68009
    Prev
    Next
    INDEX
    Explanations

    BlackBerry application

    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
     geschenk
    -1.87
     juſ
    -1.80
    这般
    -1.76
    立马
    -1.71
     neumáticos
    -1.62
     perſon
    -1.57
     casera
    -1.55
     reizen
    -1.55
     eenige
    -1.54
    chaussures
    -1.53
    POSITIVE LOGITS
     our
    1.96
     with
    1.91
     his
    1.71
     virtù
    1.66
     more
    1.59
    中国的
    1.58
     one
    1.55
    co
    1.55
     utilizing
    1.54
     at
    1.53
    Activations Density 0.000%

    No Known Activations