© 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. 47348
    Prev
    Next
    INDEX
    Explanations

    file is part of

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

    The neuron fires on numeric tokens (standalone numbers) in the text.

    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
    leri
    -0.92
    образие
    -0.85
    Doha
    -0.78
    ({},
    -0.78
    izienz
    -0.77
    ことがあります
    -0.76
    飆
    -0.76
     MotionEvent
    -0.75
    ške
    -0.75
     ASSOCIATED
    -0.74
    POSITIVE LOGITS
     Treating
    0.87
     asp
    0.81
     mẫu
    0.79
    荼
    0.79
     Роди
    0.78
     теа
    0.77
     Genus
    0.75
     âgé
    0.74
     mues
    0.73
     иллюстрация
    0.73
    Activations Density 0.001%

    No Known Activations