© 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. 104761
    Prev
    Next
    INDEX
    Explanations

    by, during, with, only

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

    The neuron detects numeric tokens with decimal‐point values (floating-point numbers).

    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
     článek
    -1.72
    Wasn
    -1.70
     nové
    -1.65
    犼
    -1.59
    いかがでしたか
    -1.59
    有什麼
    -1.58
    靦
    -1.57
    currently
    -1.52
    ೢ
    -1.52
    怎麼辦
    -1.49
    POSITIVE LOGITS
     with
    1.70
     during
    1.51
     trying
    1.50
     only
    1.45
     by
    1.41
     attempting
    1.41
     as
    1.39
     before
    1.38
     without
    1.36
     emphasizing
    1.36
    Activations Density 0.074%

    No Known Activations