© 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. 72010
    Prev
    Next
    INDEX
    Explanations

    Android R.id. components

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

    The neuron is looking for programming‐language code tokens (e.g. Java identifiers, keywords, and syntax) rather than ordinary prose.

    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
    しますね
    -1.66
     have
    -1.65
    しますが
    -1.61
    colage
    -1.56
    结语
    -1.50
    ﾋ
    -1.50
     吗
    -1.49
     whose
    -1.49
    :]:
    -1.47
    可能な
    -1.46
    POSITIVE LOGITS
     '
    2.22
    '
    2.03
    "
    1.99
    colgante
    1.91
    3
    1.89
    </strong>
    1.80
    9
    1.66
    “
    1.63
     --
    1.63
    龶
    1.59
    Activations Density 0.002%

    No Known Activations