© 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. 13523
    Prev
    Next
    INDEX
    Explanations

    headings and titles

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

    The neuron activates on numeric tokens, i.e. it identifies numbers in the text.

    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
     by
    -1.34
    teries
    -1.16
    ToMany
    -1.14
     Desember
    -1.14
    moiselle
    -1.12
    vereignty
    -1.12
     Februari
    -1.10
    usive
    -1.09
    ↵
    -1.09
     any
    -1.08
    POSITIVE LOGITS
     comprenant
    1.13
     benevol
    1.12
     horrend
    1.10
    MULTIPLE
    1.10
     demor
    1.09
     protege
    1.09
     swarms
    1.09
     obfusc
    1.09
     autrement
    1.07
    Histology
    1.06
    Activations Density 0.000%

    No Known Activations