© 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. 10-GEMMASCOPE-RES-131K
    7. 65798
    Prev
    Next
    INDEX
    Explanations

    sweep

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

    The neuron responds to the sports‐related term “sweep” (and its inflected forms like “swept” or “sweeping”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     where
    -1.72
    donde
    -1.64
     fría
    -1.48
     because
    -1.43
     into
    -1.42
    entrevista
    -1.42
     první
    -1.40
     откуда
    -1.39
    файл
    -1.37
    Funktionen
    -1.36
    POSITIVE LOGITS
    }
    1.73
     crdi
    1.54
    No
    1.53
     lorsqu
    1.52
     we
    1.51
    та
    1.48
    S
    1.45
     yzf
    1.42
     liest
    1.39
    s
    1.39
    Activations Density 0.112%

    No Known Activations