© 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. 71370
    Prev
    Next
    INDEX
    Explanations

    programming and questions

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

    The neuron fires whenever the Russian word “список” (list) or its subword forms appear.

    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
     you
    -2.95
    肫
    -2.58
    %
    -2.47
    >
    -2.38
    〬
    -2.36
     apparently
    -2.34
     incrí
    -2.33
     puzzled
    -2.23
    &
    -2.19
    —
    -2.16
    POSITIVE LOGITS
    u
    3.52
    痦
    3.13
    我们
    2.69
    ו
    2.63
    鯪
    2.58
    胧
    2.56
    tlement
    2.53
    yczny
    2.50
    erintah
    2.50
    uellement
    2.50
    Activations Density 0.003%

    No Known Activations