© 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. 2573
    Prev
    Next
    INDEX
    Explanations

    times and numbers

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

    The neuron activates on numeric date‐ and time‐related tokens (e.g. digits, colons, “a.m.”/“p.m.”) and thus flags temporal expressions.

    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
    aitlin
    -0.88
    bullet
    -0.73
    Batman
    -0.70
     Mundi
    -0.70
     Nine
    -0.69
    
    -0.69
     honoured
    -0.69
    destroy
    -0.69
    NonQuery
    -0.68
    Transition
    -0.68
    POSITIVE LOGITS
    7
    1.70
     ۷
    1.22
     ۸
    1.02
    8
    0.99
     SEVEN
    0.78
    Concert
    0.77
     Doors
    0.77
     seventh
    0.75
     seven
    0.74
    Doors
    0.74
    Activations Density 0.024%

    No Known Activations