© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115898
    Prev
    Next
    INDEX
    Explanations

    operators and code structure

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

    The neuron is keyed to spotting identifier‐like tokens—words in CamelCase or all‐caps (e.g. class names, constants, section headers) 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
     milo
    -0.82
     flying
    -0.72
    rpn
    -0.71
     consciousness
    -0.69
    Lp
    -0.68
     Adapted
    -0.66
     kopf
    -0.66
    普
    -0.65
     Whistle
    -0.65
    REDU
    -0.64
    POSITIVE LOGITS
     клас
    0.73
    ushi
    0.70
    maglia
    0.68
     verlassen
    0.67
    зраст
    0.67
    agliari
    0.67
    ctivos
    0.66
     rebuilding
    0.65
    izophrenia
    0.65
     আম
    0.65
    Activations Density 0.064%

    No Known Activations