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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38345
    Prev
    Next
    INDEX
    Explanations

    permit persons to whom

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

    The neuron fires primarily on numeric tokens—digits and numbers appearing 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
     Klar
    -0.77
    ⚖
    -0.77
     Савезне
    -0.76
     Donny
    -0.76
     Hins
    -0.72
    ropathy
    -0.72
    效应
    -0.72
    后果
    -0.71
     Paulson
    -0.70
     Gere
    -0.70
    POSITIVE LOGITS
    サッカー
    0.66
    jét
    0.65
     prohibited
    0.63
     disabling
    0.62
    ci
    0.61
     Fuß
    0.61
     Gene
    0.60
    Gene
    0.60
    onese
    0.60
    是要
    0.60
    Activations Density 0.082%

    No Known Activations