© 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. 34-GEMMASCOPE-RES-131K
    7. 118809
    Prev
    Next
    INDEX
    Explanations

    the show

    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_34/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
     subdivided
    -0.79
     beantworten
    -0.75
     exemplified
    -0.74
    Ой
    -0.72
    找到
    -0.71
    ⣯
    -0.71
    Nove
    -0.70
    ört
    -0.68
     exemp
    -0.67
    jublj
    -0.67
    POSITIVE LOGITS
     show
    5.63
     shows
    4.13
    show
    3.97
     шоу
    3.16
    shows
    2.92
     Shows
    2.72
     Show
    2.63
    Shows
    2.56
    Show
    2.39
    SHOW
    2.30
    Activations Density 0.061%

    No Known Activations