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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62781
    Prev
    Next
    INDEX
    Explanations

    et al. or phase

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

    The neuron detects numerical tokens (digits or 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
    ół
    -0.79
     übrig
    -0.76
    rei
    -0.75
    涨
    -0.71
    說
    -0.71
     VIDEOTAPE
    -0.70
    Karn
    -0.69
    IAA
    -0.69
    IBI
    -0.69
    urilor
    -0.67
    POSITIVE LOGITS
    öst
    0.78
     gospodar
    0.78
    SendMessage
    0.78
    Tid
    0.75
    GridView
    0.73
     אמ
    0.72
     ases
    0.69
    CLUSIVE
    0.67
    EventBus
    0.65
    套装
    0.65
    Activations Density 0.023%

    No Known Activations