© 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. 49574
    Prev
    Next
    INDEX
    Explanations

    PHP code delimiters

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

    The neuron is tuned to pick out numeric literals (digit‐only tokens) in source 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
    
    -0.73
     zake
    -0.70
     extending
    -0.70
     протя
    -0.69
    extends
    -0.68
     extends
    -0.67
    ednesday
    -0.66
     plastica
    -0.65
     recommended
    -0.64
    Angry
    -0.63
    POSITIVE LOGITS
    hülle
    0.77
     transvers
    0.72
     стало
    0.69
     fascist
    0.68
     ousted
    0.67
     standby
    0.67
    gana
    0.67
     outpost
    0.67
     dwarf
    0.66
     myce
    0.66
    Activations Density 0.055%

    No Known Activations