© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13054
    Prev
    Next
    INDEX
    Explanations

    Farmington, comprises, Contact

    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
    所有
    -1.95
     aspiration
    -1.90
    the
    -1.88
    that
    -1.84
     labyrinth
    -1.83
     facsimile
    -1.80
    0
    -1.76
     sebagainya
    -1.75
    beispiel
    -1.75
    ↵↵↵
    -1.72
    POSITIVE LOGITS
    轳
    3.03
    媖
    2.75
    ྵ
    2.72
    .“
    2.47
    呖
    2.39
    咈
    2.33
    
    2.33
    迸
    2.31
    “
    2.31
    镚
    2.30
    Activations Density 0.002%

    No Known Activations