© 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. 68319
    Prev
    Next
    INDEX
    Explanations

    translation and localization strings

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

    This neuron strongly activates on numerical tokens (digits or 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
     of
    -1.19
    ста
    -1.02
     another
    -1.01
     from
    -0.96
    ギフト
    -0.94
     my
    -0.94
    Reader
    -0.93
     some
    -0.91
    予定です
    -0.91
     again
    -0.89
    POSITIVE LOGITS
     SAME
    1.04
    铤
    1.02
     DEI
    1.00
     ilustraciones
    1.00
     Descargar
    0.99
     тази
    0.98
     localisation
    0.98
    ditto
    0.97
     ingenieros
    0.96
     новым
    0.94
    Activations Density 0.011%

    No Known Activations