© 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. 35547
    Prev
    Next
    INDEX
    Explanations

    Ras

    np_acts-logits-general · gemini-2.5-flash-lite

    URL-like text and webpage code elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    🤨
    -1.14
     évé
    -1.03
    😠
    -1.00
    🤢
    -0.99
    😈
    -0.99
    🤪
    -0.98
     jaja
    -0.97
    😞
    -0.97
    🤮
    -0.97
     manquante
    -0.97
    POSITIVE LOGITS
     Taehyung
    1.03
    jetzt
    1.00
    Kto
    0.96
    𝗮
    0.96
     necesidades
    0.96
     búsquedas
    0.93
    嵴
    0.93
     жк
    0.93
     einst
    0.92
    pagen
    0.91
    Activations Density 0.000%

    No Known Activations