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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109679
    Prev
    Next
    INDEX
    Explanations

    legal and licensing terms

    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
    ś
    -0.93
    gantung
    -0.83
    masalah
    -0.82
    ichè
    -0.79
    czywiście
    -0.77
    ("")
    -0.75
    Indexer
    -0.73
     اله
    -0.73
    sag
    -0.73
    isAlive
    -0.72
    POSITIVE LOGITS
    כלי
    0.87
     непо
    0.79
    懲
    0.77
    miede
    0.76
    櫂
    0.75
    Dijo
    0.74
    铿
    0.73
    vák
    0.73
    ようで
    0.72
     repertorio
    0.72
    Activations Density 0.094%

    No Known Activations