© 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. 10-GEMMASCOPE-RES-131K
    7. 119803
    Prev
    Next
    INDEX
    Explanations

    permalink, location, reference

    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_10/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
     gänzlich
    -2.70
    ي
    -2.59
    遄
    -2.56
     beinahe
    -2.55
     of
    -2.53
    平日
    -2.41
    飏
    -2.39
    i
    -2.39
     glaubt
    -2.34
    $,
    -2.30
    POSITIVE LOGITS
     ‘
    2.55
     ”
    2.55
    ’)
    2.52
    ’.
    2.45
    嵎
    2.42
    ”.
    2.42
    咴
    2.42
    栳
    2.39
      
    2.38
    蚍
    2.38
    Activations Density 0.003%

    No Known Activations