© 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. 78539
    Prev
    Next
    INDEX
    Explanations

    free software

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

    The neuron strongly responds to numeric tokens (numbers or digit sequences) 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
    fld
    -0.81
    參考資料
    -0.70
     setOpen
    -0.69
    ខ
    -0.68
    Toma
    -0.68
     Pans
    -0.64
    ♪♪
    -0.62
    𝕓
    -0.62
    人の
    -0.61
    adden
    -0.60
    POSITIVE LOGITS
     Προ
    0.81
    imide
    0.71
    contact
    0.66
     지역
    0.66
    locke
    0.65
     Kash
    0.65
    thet
    0.65
     okrę
    0.65
    loops
    0.64
    EEA
    0.64
    Activations Density 0.061%

    No Known Activations