© 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. 118639
    Prev
    Next
    INDEX
    Explanations

    long strings of zeros

    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
     those
    -0.94
    莒
    -0.88
    Those
    -0.87
    Ʈ
    -0.86
     Those
    -0.85
     there
    -0.84
    )}(\
    -0.82
    حض
    -0.81
    瀋
    -0.81
     Tempat
    -0.81
    POSITIVE LOGITS
    0
    0.96
    copied
    0.90
    studied
    0.89
    scheduled
    0.88
    baye
    0.87
    lazy
    0.87
     wachsen
    0.84
     développer
    0.84
    ANY
    0.84
    Learning
    0.82
    Activations Density 0.027%

    No Known Activations