© 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. 22-GEMMASCOPE-RES-131K
    7. 11464
    Prev
    Next
    INDEX
    Explanations

    comparing numbers or finding minimum

    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
    一套
    -0.89
     preparo
    -0.87
    áž
    -0.87
     seny
    -0.87
    kologi
    -0.86
    wijs
    -0.85
     социальной
    -0.83
    ^)／
    -0.83
    ジャパン
    -0.82
    ÈNE
    -0.81
    POSITIVE LOGITS
    return
    1.06
     choice
    0.95
     izvē
    0.92
    눌
    0.89
    linewidth
    0.87
     scelta
    0.84
     kampen
    0.82
    眶
    0.82
     dzī
    0.82
     irl
    0.81
    Activations Density 0.012%

    No Known Activations