© 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. 108443
    Prev
    Next
    INDEX
    Explanations

    code includes or comments

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

    The neuron fires on structural code/configuration keywords or directives (e.g. include statements, section-header names like “inputs” or “layer,” and other code-style tokens).

    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
    anovic
    -0.80
    ⌗
    -0.74
     Bolivar
    -0.73
    Plates
    -0.71
    VARIANT
    -0.70
     Erik
    -0.68
    EVAL
    -0.68
    findAll
    -0.67
    balah
    -0.67
    ائلة
    -0.66
    POSITIVE LOGITS
     referrals
    0.75
    ⠋
    0.74
    Holo
    0.68
     hourglass
    0.68
    വാ
    0.68
    না
    0.67
    Reading
    0.67
     TRANSL
    0.66
    胯
    0.66
    rzy
    0.66
    Activations Density 0.014%

    No Known Activations