© 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. 12677
    Prev
    Next
    INDEX
    Explanations

    market research terms

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

    The neuron specializes in spotting numeric quantities (digits and 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
     lauded
    -1.23
     molto
    -1.20
     splendid
    -1.13
     alluring
    -1.12
     astonishing
    -1.10
     remarkably
    -1.10
    ’
    -1.10
    zzz
    -1.09
     immense
    -1.08
     revered
    -1.06
    POSITIVE LOGITS
     or
    1.23
    Even
    1.13
    There
    1.09
    枇
    1.08
    As
    1.08
    のお客様
    1.07
    Many
    1.00
     blatantly
    1.00
    Several
    0.98
    These
    0.98
    Activations Density 0.225%

    No Known Activations