© 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. 34-GEMMASCOPE-RES-131K
    4. 83125
    Prev
    Next
    INDEX
    Explanations

    2. description of

    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
    nytt
    -0.78
    Попис
    -0.73
    Obrázky
    -0.70
    旦
    -0.69
    VIDEO
    -0.69
    inosaur
    -0.69
    لط
    -0.68
    essor
    -0.68
    iterraneo
    -0.67
     presentó
    -0.67
    POSITIVE LOGITS
     mérit
    0.84
    indicates
    0.79
    élection
    0.77
     スマート
    0.77
    uster
    0.77
     entière
    0.77
     Liefer
    0.76
     symptômes
    0.76
     seorang
    0.76
     ámbito
    0.75
    Activations Density 0.050%

    No Known Activations