© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69873
    Prev
    Next
    INDEX
    Explanations

    center, catcher, tight end, breaststroke

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

    The neuron detects mentions of athletic playing positions (e.g. tight end, center, guard) in sports contexts.

    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
     composée
    -1.31
    不被
    -1.23
    k
    -1.20
    苅
    -1.19
    地在
    -1.19
     verschillende
    -1.18
    calculated
    -1.17
     umožňuje
    -1.16
     nabízí
    -1.16
    miljø
    -1.15
    POSITIVE LOGITS
    」
    1.41
     With
    1.41
    ),
    1.33
    usitis
    1.30
    」、
    1.29
    </h1>
    1.29
    With
    1.25
    yship
    1.23
    hearted
    1.23
    preneurship
    1.23
    Activations Density 0.074%

    No Known Activations