© 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. 70656
    Prev
    Next
    INDEX
    Explanations

    baseball actions and objects

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

    This neuron detects mentions of specific types of batted‐ball plays in baseball (e.g. ground-rule doubles, sacrifice flies, pop-ups, fly balls).

    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
    虽然
    -1.58
    .”
    -1.54
    ziale
    -1.46
     دیجیتال
    -1.44
     alſo
    -1.44
    甚至
    -1.41
     oiseau
    -1.41
    虽
    -1.38
    ETIES
    -1.37
     kilom
    -1.36
    POSITIVE LOGITS
     to
    1.70
     najbli
    1.57
     całym
    1.54
     out
    1.41
     at
    1.38
     wcześ
    1.37
     esos
    1.34
     other
    1.31
     rzeczyw
    1.31
     sytuacji
    1.30
    Activations Density 0.005%

    No Known Activations