© 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. 101000
    Prev
    Next
    INDEX
    Explanations

    programming and descriptive modifiers

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

    technical programming terms and method names in code snippets.

    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
    轳
    -2.91
     使っ
    -2.81
    ︕
    -2.75
    讴
    -2.63
    堯
    -2.53
    皝
    -2.41
    θεια
    -2.41
    鲵
    -2.36
    瑨
    -2.36
     manifests
    -2.34
    POSITIVE LOGITS
    0
    4.59
    各样的
    3.11
    section
    2.84
    7
    2.63
    3
    2.48
    5
    2.47
    6
    2.47
    g
    2.44
    ized
    2.39
    ’
    2.39
    Activations Density 0.009%

    No Known Activations