© 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. 10-GEMMASCOPE-RES-131K
    7. 90472
    Prev
    Next
    INDEX
    Explanations

    indicating rough quantities

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

    the presence of numeric quantities (especially approximate counts or percentages) 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_10/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
    明显的
    -2.47
     absolut
    -2.42
    )$.
    -2.27
    壜
    -2.27
    тися
    -2.23
     and
    -2.22
    
    -2.17
    }}{
    -2.17
    鴞
    -2.17
     interruption
    -2.16
    POSITIVE LOGITS
    er
    2.98
    .
    2.95
     regarded
    2.86
    en
    2.80
    '
    2.75
     enjoying
    2.50
    ?
    2.50
     believed
    2.44
    re
    2.39
     convincingly
    2.39
    Activations Density 0.011%

    No Known Activations