© 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. 22-GEMMASCOPE-RES-131K
    7. 72002
    Prev
    Next
    INDEX
    Explanations

    Bootstrap UI elements

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

    This neuron fires on code “banner” lines and delimiters—long runs of hyphens, comment‐style separators, and other formatting paddings in code blocks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     The
    -1.28
     much
    -1.13
     touristes
    -1.12
     wonderful
    -1.12
    /
    -1.09
     -
    -1.05
    %,
    -1.04
     deiner
    -1.04
     Psychologie
    -1.02
    景区
    -1.02
    POSITIVE LOGITS
    باس
    1.28
    omnie
    1.19
    延伸閱讀
    1.15
    ượu
    1.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.15
    Fonto
    1.14
    ᄂ
    1.14
    شارك
    1.14
    tomia
    1.14
    ób
    1.13
    Activations Density 0.033%

    No Known Activations