© 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. 98202
    Prev
    Next
    INDEX
    Explanations

    game stats and bonuses

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

    The neuron activates on numeric tokens and statistical values—i.e. occurrences of numbers, digits, or quantitative measurements.

    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
    Preise
    -1.40
     السياس
    -1.34
     muualla
    -1.15
     бампер
    -1.14
     informée
    -1.13
     ibid
    -1.13
     weeks
    -1.10
     siglas
    -1.10
    älfte
    -1.09
    нент
    -1.09
    POSITIVE LOGITS
     you
    1.45
     for
    1.09
    ättning
    1.08
     like
    1.08
    作战
    1.06
     from
    1.05
     гле
    1.02
    panda
    1.02
    hander
    1.01
     on
    1.00
    Activations Density 0.009%

    No Known Activations