© 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. 92713
    Prev
    Next
    INDEX
    Explanations

    Apple Releases

    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
     Dickens
    -0.78
     Squal
    -0.78
    iju
    -0.77
    ϊόν
    -0.76
    vara
    -0.75
     worded
    -0.75
     thickly
    -0.73
     elizabeth
    -0.73
     panto
    -0.73
     mina
    -0.72
    POSITIVE LOGITS
     Oklahoma
    1.07
     federal
    1.02
    federal
    0.97
    Oklahoma
    0.95
     Timothy
    0.95
     Waco
    0.83
    Timothy
    0.83
     government
    0.81
     stand
    0.80
    desta
    0.80
    Activations Density 0.023%

    No Known Activations