© 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. 108360
    Prev
    Next
    INDEX
    Explanations

    expiration time

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

    The neuron activates on numeric tokens (sequences of digits), i.e. it detects numbers 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
     PACE
    -0.79
    Slu
    -0.78
    attendance
    -0.76
    bap
    -0.75
    Transcript
    -0.75
     SLOW
    -0.72
     فلس
    -0.71
    Cara
    -0.70
     resultaten
    -0.70
     Çe
    -0.69
    POSITIVE LOGITS
     expiration
    4.88
     expiry
    4.59
     expire
    3.84
     expires
    3.80
    expiration
    3.55
    Expiration
    3.48
     Expiration
    3.44
    expiry
    3.20
    Expiry
    3.06
     expiring
    3.05
    Activations Density 0.058%

    No Known Activations