© 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. 34-GEMMASCOPE-RES-131K
    7. 49506
    Prev
    Next
    INDEX
    Explanations

    raise return contact

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

    The neuron fires on Boolean‐ and null‐related tokens and comparison checks (e.g. true/false/undefined and “===”/“!==”) in code.

    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
     its
    -0.87
    Trichloroethane
    -0.86
    Belo
    -0.85
    ὲν
    -0.85
     Onder
    -0.84
     tuer
    -0.84
     mengalir
    -0.82
    انة
    -0.82
    lexer
    -0.81
    ólogo
    -0.81
    POSITIVE LOGITS
    return
    1.48
     return
    0.95
    MISSING
    0.84
     海
    0.84
     gül
    0.82
     throw
    0.81
     MISSING
    0.81
    報
    0.80
     náv
    0.79
    报
    0.79
    Activations Density 0.009%

    No Known Activations