© 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. 60804
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

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

    The neuron is keyed to numeric tokens—digits, numbers, and numeric literals 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
     Mille
    -0.80
    andingan
    -0.77
     Clubhouse
    -0.76
    rité
    -0.75
    추
    -0.74
    ΡΙ
    -0.74
     remain
    -0.70
    ཉ
    -0.68
    GI
    -0.68
    NI
    -0.68
    POSITIVE LOGITS
    ková
    0.69
     droom
    0.68
     moist
    0.66
     μή
    0.65
     construed
    0.64
    UInt
    0.64
    vince
    0.63
     disprove
    0.63
     wist
    0.62
     maneras
    0.62
    Activations Density 0.040%

    No Known Activations