© 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. 34-GEMMASCOPE-RES-131K
    7. 78959
    Prev
    Next
    INDEX
    Explanations

    missing or gone

    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
     edge
    -1.54
    edge
    -1.32
    Edge
    -1.20
     Edge
    -1.13
    EDGE
    -1.05
     EDGE
    -0.95
     corner
    -0.93
     edges
    -0.88
    edges
    -0.83
    边缘
    -0.83
    POSITIVE LOGITS
     missing
    8.13
    missing
    6.72
    Missing
    6.19
     Missing
    6.00
    MISSING
    5.03
     MISSING
    4.88
    缺
    3.39
     lacking
    3.31
    缺少
    3.28
     missed
    3.19
    Activations Density 0.215%

    No Known Activations