© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7698
    Prev
    Next
    INDEX
    Explanations

    import paths

    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
    盉
    -1.91
    立马
    -1.66
    赑
    -1.65
    蚡
    -1.60
     verhind
    -1.58
    蚰
    -1.57
     kupić
    -1.57
    淠
    -1.56
    鹪
    -1.56
    ༀ
    -1.56
    POSITIVE LOGITS
    ↵
    2.30
    4
    1.73
     which
    1.72
    5
    1.69
    D
    1.63
    6
    1.58
    2
    1.57
    ↵↵
    1.55
    7
    1.55
     Like
    1.53
    Activations Density 0.006%

    No Known Activations