© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7021
    Prev
    Next
    INDEX
    Explanations

    micro concepts

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

    micro-prefixes and web/UI design elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects tokens that convey smallness or slightness (e.g. the root “micro-” and words like “slightly” or its Chinese equivalent).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    culoskeletal
    -1.65
    Also
    -1.60
    鴒
    -1.57
    鼇
    -1.56
    ového
    -1.55
    occuper
    -1.53
    ruguay
    -1.52
    AddHtmlAttribute
    -1.48
     también
    -1.45
    CodeAttribute
    -1.45
    POSITIVE LOGITS
    </sup>
    1.67
    s
    1.60
    a
    1.57
    It
    1.45
    ers
    1.41
     ankara
    1.38
    ots
    1.35
     now
    1.35
     tsa
    1.34
    landais
    1.34
    Activations Density 0.004%

    No Known Activations