© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    champion followed by domain

    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
     '
    -2.67
     intric
    -2.58
    逦
    -2.55
    栳
    -2.50
     decidedly
    -2.45
    麁
    -2.45
     continually
    -2.44
     exceptionally
    -2.41
     remarkably
    -2.34
    ınız
    -2.33
    POSITIVE LOGITS
    Without
    2.86
    Maybe
    2.66
    In
    2.55
    During
    2.53
    While
    2.52
    Often
    2.50
    You
    2.45
    Usually
    2.45
    Probably
    2.44
    Perhaps
    2.44
    Activations Density 0.012%

    No Known Activations