© 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. 22-GEMMASCOPE-RES-131K
    7. 9518
    Prev
    Next
    INDEX
    Explanations

    Linux file paths

    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
    <bos>
    -1.98
    を
    -1.96
    と
    -1.78
    ですが
    -1.61
    醍
    -1.59
    ernoo
    -1.53
    があり
    -1.47
    
    -1.47
    人と
    -1.41
    動機
    -1.41
    POSITIVE LOGITS
    為に
    1.80
    ほら
    1.65
    ところに
    1.63
    えっ
    1.59
    あー
    1.59
    つづく
    1.55
    にします
    1.49
    ええ
    1.49
    に行って
    1.48
    に入れる
    1.47
    Activations Density 0.027%

    No Known Activations