© 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. 10-GEMMASCOPE-RES-131K
    7. 15007
    Prev
    Next
    INDEX
    Explanations

    quantities of time

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

    The neuron triggers on numeric tokens containing a decimal point (i.e. fractional 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
    ⑊
    -2.53
    ";
    -2.08
    おはよう
    -2.02
     جديدة
    -1.84
     ſhe
    -1.83
    by
    -1.81
     retten
    -1.80
     tbsp
    -1.78
     poches
    -1.78
     tunggal
    -1.77
    POSITIVE LOGITS
     häufigsten
    2.16
     wichtigste
    2.08
     This
    2.08
     mantend
    2.05
     People
    1.95
     merkwür
    1.95
     beliebtesten
    1.91
     limitations
    1.91
    して下さい
    1.84
     was
    1.84
    Activations Density 0.212%

    No Known Activations