© 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. 64008
    Prev
    Next
    INDEX
    Explanations

    remove code

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

    The neuron strongly responds to numeral tokens (i.e. numbers) in the document.

    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
    reinterpret
    -0.70
    vii
    -0.70
    hii
    -0.69
    前回
    -0.68
     Bray
    -0.68
    Nay
    -0.67
    hã
    -0.66
    Hidden
    -0.66
    璋
    -0.66
    rei
    -0.65
    POSITIVE LOGITS
    ⦃
    0.69
    ชาติ
    0.69
    録音
    0.66
    ciles
    0.66
     Torrance
    0.64
    (())
    0.64
    𝕡
    0.64
     Argyle
    0.63
     biểu
    0.63
     chloride
    0.62
    Activations Density 0.059%

    No Known Activations