© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 268
    Prev
    Next
    INDEX
    Explanations

    headings or section titles

    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
     etc
    -1.40
    もあります
    -1.38
    があります
    -1.34
    そして
    -1.33
    Итак
    -1.31
    などを
    -1.30
    捗
    -1.28
    がありますが
    -1.27
     abbraccio
    -1.26
     of
    -1.21
    POSITIVE LOGITS
    来週
    1.41
    割と
    1.27
    さっそく
    1.26
    の商品
    1.24
    に入れ
    1.20
    ほら
    1.16
    の時に
    1.16
    の前に
    1.14
    ことも
    1.12
    感じで
    1.12
    Activations Density 0.918%

    No Known Activations