© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59859
    Prev
    Next
    INDEX
    Explanations

    numerical time periods

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

    the presence of numeric tokens (multi-digit numbers and measurements) 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
     hours
    -1.49
    hours
    -1.30
     hour
    -1.29
     Hours
    -1.27
    Hours
    -1.24
    hour
    -1.23
     часа
    -1.14
     horas
    -1.10
    Hour
    -1.05
    Two
    -1.03
    POSITIVE LOGITS
     ten
    2.44
     fifteen
    2.41
     Fifteen
    2.11
     twenty
    2.00
    Fifteen
    1.92
    十分钟
    1.70
     zehn
    1.58
     minutes
    1.56
     veinte
    1.52
    Twenty
    1.50
    Activations Density 0.047%

    No Known Activations