© 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. 71969
    Prev
    Next
    INDEX
    Explanations

    code syntax and symbols

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

    The neuron is keyed to the percent sign (%) in string literals, i.e. it detects printf‐style format specifiers.

    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
    2
    -2.69
    This
    -2.30
    what
    -2.28
    6
    -2.19
    with
    -2.19
    le
    -2.19
    If
    -2.17
    $
    -2.11
    3
    -2.08
    Taking
    -2.00
    POSITIVE LOGITS
    鼍
    2.19
     constantemente
    2.11
    閦
    2.03
    鶫
    1.99
    伥
    1.97
    鉝
    1.85
    nodoc
    1.81
     برانيه
    1.77
    がいい
    1.73
    assassin
    1.73
    Activations Density 0.005%

    No Known Activations