© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73900
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     chasm
    -0.91
     how
    -0.89
     remarkably
    -0.88
    more
    -0.87
    犷
    -0.86
    ard
    -0.83
    ila
    -0.81
    ±
    -0.81
    can
    -0.80
    neden
    -0.79
    POSITIVE LOGITS
    ٦
    0.93
    Vod
    0.88
    Jahre
    0.86
     appareil
    0.86
    junta
    0.84
    Czy
    0.83
    рации
    0.83
    pięk
    0.82
     опять
    0.82
     jardin
    0.82
    Activations Density 0.002%

    No Known Activations