© 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. 14178
    Prev
    Next
    INDEX
    Explanations

    code comments author tags

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

    The neuron fires on long asterisk‐prefixed comment lines in source code—especially those carrying metadata like version or license information.

    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
    providedIn
    -1.27
     which
    -1.16
     by
    -1.07
    MeasureSpec
    -1.00
    splitlines
    -0.99
     new
    -0.97
     pure
    -0.97
     most
    -0.96
     so
    -0.96
     sœurs
    -0.95
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.14
     @{
    1.14
    änderung
    1.13
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.09
    Tecnología
    1.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.05
     vetores
    1.03
    ucción
    1.03
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.02
    Kepala
    1.02
    Activations Density 0.011%

    No Known Activations