© 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. 109920
    Prev
    Next
    INDEX
    Explanations

    code comments and declarations

    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
     all
    -0.90
     jeho
    -0.88
     partially
    -0.86
     blue
    -0.85
     gave
    -0.85
     bringing
    -0.80
     blatantly
    -0.79
     Tel
    -0.78
     as
    -0.77
    硯
    -0.76
    POSITIVE LOGITS
     intertw
    0.93
     castig
    0.91
     subst
    0.91
    fatta
    0.90
    uska
    0.90
     xan
    0.89
     admon
    0.87
     costante
    0.86
    當然
    0.84
     Justine
    0.83
    Activations Density 0.002%

    No Known Activations