© 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. 6864
    Prev
    Next
    INDEX
    Explanations

    USTC | underground storage tanks

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

    The neuron strongly activates on tokens beginning with the letter “U” (i.e. uppercase U-initial strings).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    '
    -3.22
    <bos>
    -2.84
    袛
    -2.55
    鸸
    -2.53
    不断的
    -2.53
    Of
    -2.47
    菒
    -2.45
     россии
    -2.39
    ",
    -2.38
    戋
    -2.38
    POSITIVE LOGITS
    s
    3.16
    етки
    3.03
    та
    2.59
     suced
    2.42
    ?</
    2.42
    𖣘
    2.38
    ↵↵
    2.38
     intoxicating
    2.33
     encontr
    2.30
    ⟐
    2.25
    Activations Density 0.073%

    No Known Activations