© 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. 34-GEMMASCOPE-RES-131K
    7. 106412
    Prev
    Next
    INDEX
    Explanations

    Boost software license

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

    This neuron activates on numeric tokens (digits or numbers) in code, such as version numbers or other numeric literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     户型
    -0.82
     вопроса
    -0.82
     молоко
    -0.80
     architect
    -0.80
     タイヤ
    -0.79
    mão
    -0.76
     DOUGLAS
    -0.73
    ̛
    -0.73
    🥷
    -0.72
    表演
    -0.72
    POSITIVE LOGITS
     mayhem
    1.01
    metres
    0.98
     Mayhem
    0.93
     unquestion
    0.85
    OkHttpClient
    0.84
    Escrito
    0.84
     کردیم
    0.82
    henden
    0.81
    Tanto
    0.79
     lovely
    0.77
    Activations Density 0.415%

    No Known Activations