© 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. 22-GEMMASCOPE-RES-131K
    7. 36714
    Prev
    Next
    INDEX
    Explanations

    a [noun]

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

    The neuron activates on three-digit numeral tokens (i.e. numbers of the form “###”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    nasi
    -1.39
    atique
    -1.30
    了些
    -1.27
    (/^
    -1.23
    antry
    -1.23
    nastics
    -1.23
     possib
    -1.23
     ۱۰
    -1.22
    ciled
    -1.22
    artments
    -1.22
    POSITIVE LOGITS
     recently
    1.67
     very
    1.59
     that
    1.49
     nearby
    1.45
     other
    1.37
     previously
    1.37
     our
    1.36
     small
    1.35
     previous
    1.34
     recent
    1.34
    Activations Density 0.088%

    No Known Activations