© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118178
    Prev
    Next
    INDEX
    Explanations

    import/export and linking library

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

    The neuron fires on numeric tokens and digit sequences (e.g. error codes, version numbers, or other multi‐digit constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ẳ
    -0.67
    getValue
    -0.67
     Dulce
    -0.66
    bleed
    -0.66
    かい
    -0.65
     ベビー
    -0.64
    transforms
    -0.63
    Flashback
    -0.62
    閉
    -0.62
    variable
    -0.61
    POSITIVE LOGITS
     export
    1.38
     exports
    1.33
     imports
    1.30
     import
    1.27
     Export
    1.23
     Import
    1.16
    imports
    1.06
    Export
    1.05
     Exports
    1.04
     importing
    0.99
    Activations Density 0.039%

    No Known Activations