© 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. 10-GEMMASCOPE-RES-131K
    7. 709
    Prev
    Next
    INDEX
    Explanations

    licenses, minister, ROW, multiline text

    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
     glyphicon
    -1.70
     behulp
    -1.63
     gebouw
    -1.61
     uitzicht
    -1.52
     this
    -1.44
     and
    -1.44
    such
    -1.44
     мысль
    -1.41
    tedì
    -1.39
    ấc
    -1.38
    POSITIVE LOGITS
     erweitert
    1.95
    </em>
    1.64
    에도
    1.56
    DEPORT
    1.55
     They
    1.55
    他的
    1.54
     verbessert
    1.53
    
    1.52
     oubli
    1.52
     remota
    1.49
    Activations Density 0.002%

    No Known Activations