© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113540
    Prev
    Next
    INDEX
    Explanations

    Q: Altorfer Inc

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

    This neuron fires on the “=>” token used to separate keys from values in code (e.g., in associative arrays or parameter bindings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     by
    -1.85
    .
    -1.73
     what
    -1.50
    ;
    -1.47
    ');
    -1.47
    1
    -1.46
     When
    -1.42
     when
    -1.37
    </i>
    -1.37
    ‘
    -1.34
    POSITIVE LOGITS
     számára
    1.67
    嵓
    1.65
     этих
    1.56
    俞
    1.54
    欧阳
    1.53
     pokoje
    1.53
     comentários
    1.52
     sérieux
    1.48
    Tämä
    1.48
    皛
    1.48
    Activations Density 0.001%

    No Known Activations