© 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. 10-GEMMASCOPE-RES-131K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The main thing this neuron does is detect numeric tokens (e.g. years, counts, or statistical values).

    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
    -2.63
    },
    -2.33
    ophageal
    -2.30
    daging
    -2.28
     musíte
    -2.20
    iniai
    -2.13
    ranslated
    -2.03
    $,
    -2.03
    нью
    -2.02
    kość
    -1.98
    POSITIVE LOGITS
     the
    2.59
    茈
    2.34
    end
    2.28
     been
    2.09
     começ
    2.08
     ")
    2.05
    no
    2.00
    ⼗
    1.96
    ętr
    1.95
    当即
    1.95
    Activations Density 0.325%

    No Known Activations