© 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. 91849
    Prev
    Next
    INDEX
    Explanations

    photographic technical

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

    The neuron specializes in detecting numeric tokens—especially multi‐digit numbers and years—throughout 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
    Phương
    -0.77
    荠
    -0.72
    ObjectModel
    -0.70
     Peers
    -0.70
     Pythagoras
    -0.68
     Inner
    -0.68
    observation
    -0.67
    Sell
    -0.67
    Inner
    -0.67
     考
    -0.67
    POSITIVE LOGITS
     infrared
    0.69
     Infrared
    0.68
     huden
    0.68
    houettes
    0.68
     forecasts
    0.68
    police
    0.67
    endio
    0.66
     iba
    0.66
    Infrared
    0.65
    ッシング
    0.65
    Activations Density 0.033%

    No Known Activations