© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55936
    Prev
    Next
    INDEX
    Explanations

    references and citations

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

    This neuron detects multi-digit numerical tokens (long sequences of digits, such as four-digit numbers or larger).

    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
    作品の
    -0.89
     phá
    -0.85
    顶部
    -0.81
    NOMBRE
    -0.80
     liggen
    -0.79
    .¹
    -0.77
    quait
    -0.77
     disagrees
    -0.76
    合わせる
    -0.76
    brium
    -0.74
    POSITIVE LOGITS
     REF
    0.99
    REF
    0.87
    Refer
    0.82
     clues
    0.79
    ref
    0.78
    Ref
    0.77
    稻
    0.77
    参照
    0.76
    FI
    0.75
     Ref
    0.74
    Activations Density 0.087%

    No Known Activations