© 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. 48522
    Prev
    Next
    INDEX
    Explanations

    academic semesters and trimesters

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

    The neuron fires on numeric tokens (integers and decimals).

    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
    憮
    -1.81
     sebelum
    -1.76
    ⡦
    -1.72
     tetapi
    -1.66
     deemed
    -1.63
     voordat
    -1.62
    dámské
    -1.61
    낍
    -1.61
     jaula
    -1.59
    寕
    -1.59
    POSITIVE LOGITS
    )
    2.08
    /*
    1.91
    (
    1.86
    We
    1.70
     H
    1.66
    reathable
    1.65
    I
    1.65
     invierno
    1.65
     asomb
    1.65
     vời
    1.58
    Activations Density 0.003%

    No Known Activations