© 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. 117666
    Prev
    Next
    INDEX
    Explanations

    free software license

    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
     convirtió
    -0.87
    場所は
    -0.82
     kılıf
    -0.82
     najdete
    -0.82
    Страна
    -0.82
     Drogen
    -0.81
    Украина
    -0.81
     cuchara
    -0.81
     vacía
    -0.80
     فره
    -0.79
    POSITIVE LOGITS
     software
    1.31
     program
    1.06
    ɩ
    1.02
     work
    0.95
    software
    0.95
    SOFTWARE
    0.88
    балан
    0.88
    %$$
    0.87
    oftware
    0.86
    Software
    0.86
    Activations Density 0.630%

    No Known Activations