© 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. 34-GEMMASCOPE-RES-131K
    7. 117384
    Prev
    Next
    INDEX
    Explanations

    one of

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

    The neuron primarily responds to numeric tokens (i.e. standalone numbers and digit sequences).

    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
     pink
    -0.74
    讫
    -0.74
     क्योंकि
    -0.74
    гию
    -0.72
    logram
    -0.72
     bargaining
    -0.71
     judgment
    -0.70
    ArgumentParser
    -0.70
     character
    -0.69
     dice
    -0.69
    POSITIVE LOGITS
     Klon
    0.95
    gemeen
    0.86
    berian
    0.85
     talon
    0.81
    stö
    0.79
    TypeString
    0.79
    tacular
    0.77
    stock
    0.76
     piles
    0.75
    buzo
    0.75
    Activations Density 0.011%

    No Known Activations