© 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. 103444
    Prev
    Next
    INDEX
    Explanations

    line numbers and source map

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

    references to line numbers in technical or programming contexts.

    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
     Despite
    -2.13
     When
    -2.08
     There
    -2.03
     Being
    -2.00
     IN
    -1.98
     Having
    -1.97
     !!
    -1.96
     Even
    -1.91
    ",
    -1.88
     Although
    -1.88
    POSITIVE LOGITS
    癭
    2.31
    และ
    2.00
    搋
    1.98
     ランプ
    1.98
    ⏑
    1.98
     流れ
    1.94
    despite
    1.94
    神
    1.93
     predominantly
    1.92
     墊
    1.91
    Activations Density 0.004%

    No Known Activations