© 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. 110875
    Prev
    Next
    INDEX
    Explanations

    version of

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

    This neuron detects numeric tokens (standalone digits or numbers, e.g. version numbers, years, IDs).

    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
     cứu
    -0.76
    PRD
    -0.71
     fabric
    -0.70
    fabric
    -0.70
    PopupWindow
    -0.68
     regular
    -0.67
     goreng
    -0.66
    gaon
    -0.66
    펄
    -0.64
    code
    -0.63
    POSITIVE LOGITS
    ⓙ
    0.72
    做过
    0.71
     INDUSTR
    0.69
    🅜
    0.67
    añ
    0.66
    maran
    0.66
     onyx
    0.66
     Sem
    0.65
     otaku
    0.65
     atop
    0.64
    Activations Density 0.077%

    No Known Activations