© 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. 99310
    Prev
    Next
    INDEX
    Explanations

    predictors | Hollingstedt | I know

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

    This neuron fires on code-comment lines and headers (especially the “// …” license‐header and metadata comment blocks).

    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
    áš
    -0.78
     perceptual
    -0.74
     Blockchain
    -0.70
    票
    -0.70
    años
    -0.70
    Clin
    -0.69
     Grosse
    -0.69
    Hoc
    -0.67
    ________________
    -0.66
     choirs
    -0.66
    POSITIVE LOGITS
     Geschichts
    0.84
     hikay
    0.83
     része
    0.83
     plomo
    0.80
    渟
    0.79
    梆
    0.77
    HeaderComponent
    0.77
     Mackay
    0.75
    Veterans
    0.75
     女の子
    0.75
    Activations Density 0.003%

    No Known Activations