© 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. 34-GEMMASCOPE-RES-131K
    7. 48713
    Prev
    Next
    INDEX
    Explanations

    documentation headers or directives

    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_34/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
     our
    -1.27
     nuestros
    -1.08
    疹
    -1.04
     szerint
    -1.01
    我們
    -1.01
     naszych
    -1.01
     növény
    -0.99
    我们
    -0.97
     hulle
    -0.96
    ándonos
    -0.95
    POSITIVE LOGITS
     you
    1.65
     usage
    1.63
     tested
    1.60
     requires
    1.56
     Tested
    1.48
     enjoy
    1.47
     currently
    1.44
     Requires
    1.41
    tested
    1.37
    Tested
    1.34
    Activations Density 0.152%

    No Known Activations