© 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. 10-GEMMASCOPE-RES-131K
    7. 586
    Prev
    Next
    INDEX
    Explanations

    attributing information

    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_10/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
     aDecoder
    -1.88
    푣
    -1.77
     gehört
    -1.72
    tences
    -1.67
    灃
    -1.62
    на
    -1.60
    ︹
    -1.55
    bellar
    -1.51
     ktorí
    -1.49
    获取
    -1.48
    POSITIVE LOGITS
    $
    1.92
     its
    1.92
    st
    1.87
    ti
    1.77
    却被
    1.75
     behulp
    1.75
     their
    1.70
     grij
    1.64
    ⸫
    1.62
    er
    1.61
    Activations Density 0.014%

    No Known Activations