© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11292
    Prev
    Next
    INDEX
    Explanations

    just or only

    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
    を
    -2.11
     in
    -2.02
     for
    -1.85
    や
    -1.80
    と
    -1.74
     to
    -1.68
     by
    -1.68
     after
    -1.64
     during
    -1.62
    などを
    -1.62
    POSITIVE LOGITS
    為に
    1.95
    ところに
    1.88
    corrhi
    1.75
    ほら
    1.61
    ようになって
    1.58
     a
    1.56
    ようになる
    1.55
    ようです
    1.54
    必要がある
    1.52
    ごとの
    1.52
    Activations Density 0.049%

    No Known Activations