© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103732
    Prev
    Next
    INDEX
    Explanations

    sports pitch

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

    The main thing this neuron does is detect occurrences of the word “pitch.”

    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
    The
    -3.06
    0
    -2.61
    –
    -2.59
    酲
    -2.59
    A
    -2.58
    2
    -2.48
     –
    -2.45
     encompassing
    -2.41
     mereka
    -2.38
     \
    -2.36
    POSITIVE LOGITS
    沕
    3.02
    ſſi
    2.98
    茕
    2.95
    圌
    2.58
    不断的
    2.58
    鼱
    2.55
    鞮
    2.47
    潆
    2.47
     cuida
    2.45
    ⭓
    2.42
    Activations Density 0.004%

    No Known Activations