© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 337
    Prev
    Next
    INDEX
    Explanations

    file variable assignment

    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
    accor
    -0.91
     SolutionA
    -0.87
     Techniques
    -0.82
    gulama
    -0.79
     hacían
    -0.77
     unicornio
    -0.75
    hdashline
    -0.75
    🟧
    -0.74
    portug
    -0.74
     duża
    -0.73
    POSITIVE LOGITS
    mm
    0.82
    ={<
    0.81
    锈
    0.80
    kat
    0.79
    ógio
    0.79
     ambos
    0.77
    apk
    0.76
     datasets
    0.76
    ppan
    0.75
    HELP
    0.75
    Activations Density 0.168%

    No Known Activations