© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14702
    Prev
    Next
    INDEX
    Explanations

    code strings and section headers

    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
     everyone
    -0.96
    WireFormat
    -0.86
    周泽楷
    -0.86
    резать
    -0.82
    loyed
    -0.82
     vigne
    -0.81
    LEBR
    -0.80
     goc
    -0.80
     calendriers
    -0.79
     Sentin
    -0.79
    POSITIVE LOGITS
     is
    0.96
    Still
    0.91
    bosis
    0.89
    Eight
    0.85
     целый
    0.84
     четырех
    0.84
    かというと
    0.83
     Impressive
    0.82
    ikko
    0.80
     should
    0.79
    Activations Density 0.000%

    No Known Activations