© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7129
    Prev
    Next
    INDEX
    Explanations

    FN, VOC, UF, STD, lex

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

    The neuron consistently fires on short uppercase letter sequences (acronyms/abbreviations like “FN,” “UF,” “VOC”) and similar letter‐only 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_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
    逦
    -3.44
    龊
    -3.36
    蜴
    -3.17
    ꙮ
    -2.98
     природа
    -2.95
    limia
    -2.67
     potřeb
    -2.50
    dollis
    -2.45
    狁
    -2.45
    ۥ
    -2.44
    POSITIVE LOGITS
    *
    3.95
    0
    2.78
    1
    2.75
    </strong>
    2.64
    感じ
    2.59
     they
    2.53
    8
    2.48
    就不是
    2.47
    6
    2.47
    7
    2.41
    Activations Density 0.005%

    No Known Activations