© 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. 75101
    Prev
    Next
    INDEX
    Explanations

    winning races

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

    The neuron activates on mentions of horses’ racing performance statistics (numbers of wins, races, starts, etc.).

    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
     this
    -1.27
     和
    -1.19
     the
    -1.17
     mieć
    -1.12
     an
    -1.11
    無し
    -1.10
    さんへ
    -1.10
     a
    -1.10
     such
    -1.09
     being
    -1.09
    POSITIVE LOGITS
    تفسير
    1.20
     治療
    1.20
    تحميل
    1.19
    zette
    1.09
    つまり
    1.07
     naší
    1.07
    參見
    1.07
    Honor
    1.06
     jeder
    1.06
    เคย
    1.05
    Activations Density 0.000%

    No Known Activations