© 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. 39995
    Prev
    Next
    INDEX
    Explanations

    conditional logic

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

    The neuron is specialized to pick out numeric literals (sequences of 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_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
     of
    -1.54
     Projektu
    -1.25
     where
    -1.24
     OGSÅ
    -1.24
     for
    -1.22
     Konkur
    -1.21
     alkoh
    -1.19
     from
    -1.13
     Kompet
    -1.11
     ideen
    -1.07
    POSITIVE LOGITS
     ciertos
    1.53
     ciertas
    1.32
     determinados
    1.22
    Chiara
    1.20
     determinadas
    1.16
    uktion
    1.16
    inaire
    1.11
     bestimmten
    1.09
     práctico
    1.09
     creencias
    1.08
    Activations Density 0.001%

    No Known Activations