© 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. 34-GEMMASCOPE-RES-131K
    7. 23790
    Prev
    Next
    INDEX
    Explanations

    brom/bram-start words

    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
     ugly
    -0.85
    穎
    -0.78
     paix
    -0.73
    ugly
    -0.73
    ENNA
    -0.71
     unsightly
    -0.70
    行った
    -0.69
    ตรี
    -0.68
    Moneda
    -0.68
     chắn
    -0.67
    POSITIVE LOGITS
    Pau
    0.79
    хли
    0.76
    investissement
    0.75
    skou
    0.75
    Hence
    0.74
     skrzy
    0.74
    nesc
    0.74
    sigt
    0.73
    RTDA
    0.71
    ünst
    0.71
    Activations Density 0.015%

    No Known Activations