© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48992
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and durations

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

    The neuron activates on numeric tokens or quantifiers (digits and number words) 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
    软件特色
    -0.79
    櫃
    -0.75
     хвати
    -0.73
     된
    -0.72
    游戏亮点
    -0.71
     TCR
    -0.68
     съ
    -0.67
     IPT
    -0.66
    giat
    -0.66
     arra
    -0.65
    POSITIVE LOGITS
     ninety
    2.50
     eighty
    1.66
     Ninety
    1.61
     sixty
    1.56
    Nin
    1.51
     seventy
    1.51
     forty
    1.34
     full
    1.20
     regulation
    1.19
     Sixty
    1.19
    Activations Density 0.021%

    No Known Activations