© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106908
    Prev
    Next
    INDEX
    Explanations

    and then symbols

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

    The neuron activates on numeric tokens—i.e. it detects occurrences of numbers (digits) 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_34/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
     outras
    -1.38
    その他
    -1.38
     andere
    -1.30
     innych
    -1.29
     OTHER
    -1.27
    镲
    -1.23
     .........
    -1.18
    其他
    -1.17
     altre
    -1.16
    ほか
    -1.16
    POSITIVE LOGITS
     one
    1.48
     its
    1.46
     so
    1.23
     trattano
    1.16
     when
    1.16
     after
    1.15
     from
    1.12
     then
    1.11
     with
    1.08
     during
    1.08
    Activations Density 0.100%

    No Known Activations