© 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. 22-GEMMASCOPE-RES-131K
    7. 79832
    Prev
    Next
    INDEX
    Explanations

    code blocks and definitions

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

    The neuron is detecting numeric literals (tokens that represent numbers or numeric constants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ຶ
    -1.08
     bestaan
    -0.97
    かわらず
    -0.94
     violación
    -0.91
     acestui
    -0.90
     asistentes
    -0.88
     représentent
    -0.88
    composed
    -0.88
    BEFORE
    -0.86
    zzz
    -0.85
    POSITIVE LOGITS
     if
    1.01
     disliked
    0.86
    вле
    0.85
    طه
    0.84
     with
    0.82
     new
    0.79
    艺术家
    0.79
     both
    0.76
    べる
    0.76
    0.75
    Activations Density 0.002%
    No Known Activations