© 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. 22-GEMMASCOPE-RES-131K
    7. 128334
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens—sequences of digits representing parameter or configuration values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    frequency and baud rates

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cubierto
    -1.25
     teams
    -1.23
     all
    -1.20
    parsedMessage
    -1.13
     there
    -1.09
     ιστο
    -1.08
     previous
    -1.06
     rígida
    -1.05
    ARROLLO
    -1.05
     pintado
    -1.04
    POSITIVE LOGITS
    thargy
    1.29
    Angebot
    1.21
    träglich
    1.20
     baud
    1.16
     fout
    1.14
     Lien
    1.11
    siehe
    1.11
    oció
    1.10
     resolu
    1.10
    teilte
    1.07
    Activations Density 0.010%

    No Known Activations