© 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. 22-GEMMASCOPE-RES-131K
    7. 65138
    Prev
    Next
    INDEX
    Explanations

    `id` followed by comma

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

    The neuron fires on programming identifiers and related code symbols (e.g. CamelCase names, annotation names, or header/file paths).

    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
     being
    -0.90
    satunya
    -0.86
    いただいて
    -0.85
    uchtung
    -0.84
     سكان
    -0.82
     书
    -0.81
     presencia
    -0.79
    geometric
    -0.79
    风的
    -0.78
    nější
    -0.77
    POSITIVE LOGITS
     verschieden
    1.04
    ]');
    1.02
    ถ
    1.02
     différentes
    1.00
     ниж
    0.94
     of
    0.91
    خاص
    0.91
    mped
    0.91
    вих
    0.90
     mág
    0.90
    Activations Density 0.000%

    No Known Activations