© 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. 22-GEMMASCOPE-RES-131K
    7. 25437
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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_22/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
     좋
    -0.88
    Sze
    -0.87
    exemplar
    -0.85
    ľov
    -0.83
     fejl
    -0.82
    anovic
    -0.79
    6
    -0.77
    避け
    -0.77
     jenis
    -0.77
     first
    -0.76
    POSITIVE LOGITS
     Giappone
    0.91
    瓊
    0.90
     ministra
    0.88
     Lenn
    0.85
     Vaugh
    0.84
    getAbsolutePath
    0.84
    rdoba
    0.84
    Conclusão
    0.82
     auteurs
    0.82
     ज़
    0.82
    Activations Density 0.003%

    No Known Activations