© 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. 103361
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    words or tokens related to dental or anatomical structures (particularly "inode", "denti-" prefixes, and names like "Framingham").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    2
    -3.11
    塒
    -3.06
    8
    -3.06
    7
    -3.02
    With
    -3.02
    All
    -2.97
    4
    -2.92
    One
    -2.91
    which
    -2.89
    Only
    -2.88
    POSITIVE LOGITS
    翃
    3.08
     แต่
    3.05
    刳
    2.81
    籮
    2.77
    
    2.67
     antigas
    2.64
     it
    2.59
    ￪
    2.52
    瘰
    2.45
     monstrous
    2.42
    Activations Density 0.028%

    No Known Activations