© 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. 12389
    Prev
    Next
    INDEX
    Explanations

    head coach,morgan phillips, tiger woods, solar electricity

    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
     mezzi
    -0.90
     읽
    -0.88
    ㆁ
    -0.88
    TSCA
    -0.86
     masques
    -0.86
     esthétique
    -0.86
     ganska
    -0.85
     案例
    -0.85
     彩色
    -0.85
    出一个
    -0.84
    POSITIVE LOGITS
    Gri
    0.80
     i
    0.80
    Closer
    0.79
    thread
    0.77
     here
    0.77
     plus
    0.77
    !
    0.77
    фера
    0.76
     include
    0.75
     Thread
    0.75
    Activations Density 0.026%

    No Known Activations