© 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. 22-GEMMASCOPE-RES-131K
    7. 33472
    Prev
    Next
    INDEX
    Explanations

    percentages and dollar amounts

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

    This neuron activates on numeric tokens, i.e. sequences of digits representing quantities or figures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     喜欢
    -0.97
    insured
    -0.84
    Sind
    -0.82
     pesto
    -0.78
     marque
    -0.76
    ບ
    -0.75
    ctron
    -0.73
     junho
    -0.73
    ピック
    -0.72
    teza
    -0.72
    POSITIVE LOGITS
    <>
    0.85
    Çok
    0.83
    Jangan
    0.83
    Warna
    0.75
    zzjoni
    0.75
     this
    0.74
     as
    0.73
    Давайте
    0.73
    ՛
    0.73
    tempat
    0.73
    Activations Density 0.020%

    No Known Activations