© 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. 64761
    Prev
    Next
    INDEX
    Explanations

    unit/quantity manipulation

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

    The neuron responds to non-lowercase tokens—especially punctuation marks (like “.”), acronyms, and other all-caps or symbol-heavy 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
    架构
    -0.71
    lastic
    -0.70
    痕迹
    -0.69
    CHAMP
    -0.68
    儿的
    -0.68
     дов
    -0.68
     Everything
    -0.68
     J
    -0.68
     behave
    -0.68
    更换
    -0.68
    POSITIVE LOGITS
    ीय
    0.83
    iação
    0.79
    express
    0.79
     finan
    0.77
    '".
    0.77
    ABULARY
    0.77
    Curve
    0.76
    ]=\
    0.76
    Cole
    0.76
    nessed
    0.76
    Activations Density 0.002%

    No Known Activations