© 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. 12429
    Prev
    Next
    INDEX
    Explanations

    HTML tag delimiters and code blocks

    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
     separate
    -0.85
    Engl
    -0.85
     occurrences
    -0.85
    不一定
    -0.84
    只有一
    -0.84
    当時の
    -0.83
     Erinnerung
    -0.83
     Geschä
    -0.82
     Something
    -0.82
     jederzeit
    -0.82
    POSITIVE LOGITS
    </b>
    1.00
     われ
    0.95
     САД
    0.93
    ⅼ
    0.88
     Maintenant
    0.88
     män
    0.87
    hadapi
    0.85
     pamoja
    0.85
     kanyang
    0.84
     boks
    0.82
    Activations Density 0.020%

    No Known Activations