© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77686
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and time periods

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

    This neuron detects mid‐game temporal or segment markers in sports play-by-play (e.g. "entering the second half," "bottom of the sixth inning").

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ilig
    -0.86
    hasia
    -0.84
    ensan
    -0.77
    ISHING
    -0.76
     lig
    -0.75
     wavelet
    -0.74
     Năm
    -0.73
    hoten
    -0.73
    DEVICES
    -0.73
     faite
    -0.72
    POSITIVE LOGITS
     frame
    2.25
    frame
    1.75
    Frame
    1.71
     frames
    1.64
     stanza
    1.63
     Frame
    1.59
     FRAME
    1.59
    フレーム
    1.44
     period
    1.36
     Frames
    1.31
    Activations Density 0.033%

    No Known Activations