© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    codes and numbers

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

    numeric codes or identifiers, particularly those containing "20" followed by additional digits.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on numeric tokens (especially multi-digit and decimal numbers).

    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
     ''
    -1.67
     his
    -1.65
     mantiene
    -1.56
    して下さい
    -1.53
    というのは
    -1.53
    除去
    -1.52
    キッズ
    -1.51
     nécessaire
    -1.50
     また
    -1.49
    入院
    -1.49
    POSITIVE LOGITS
    “,
    1.84
    ’
    1.80
    (",
    1.75
    ಼
    1.68
     where
    1.65
     and
    1.64
    /-
    1.63
     unserer
    1.50
    er
    1.49
    {
    1.47
    Activations Density 0.091%

    No Known Activations