© 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. 92527
    Prev
    Next
    INDEX
    Explanations

    roll probability

    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
     Aeronautics
    -0.75
     Ramesh
    -0.73
     отда
    -0.72
    ́i
    -0.72
    митри
    -0.71
    ハンバーグ
    -0.71
    المشاركات
    -0.70
     Suez
    -0.69
    ToProps
    -0.66
     nmax
    -0.66
    POSITIVE LOGITS
     roll
    4.84
     rolls
    4.16
     rolled
    3.97
    Roll
    3.92
    roll
    3.91
     Roll
    3.81
     rolling
    3.55
    ROLL
    3.45
     ROLL
    3.30
    Rolls
    3.08
    Activations Density 0.042%

    No Known Activations