© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    specifying real-world values

    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
     -
    -3.08
     "
    -2.63
    ].
    -2.42
     :).
    -2.36
     ако
    -2.36
    ".
    -2.34
     fünf
    -2.34
    <
    -2.33
     [
    -2.23
    ."
    -2.14
    POSITIVE LOGITS
    衕
    2.92
    ～♪
    2.92
    ～　
    2.91
    ?”
    2.86
    ⸒
    2.84
    li
    2.70
    
    2.69
    ↵
    2.67
    s
    2.61
    ＼(^
    2.56
    Activations Density 0.009%

    No Known Activations