© 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. 78744
    Prev
    Next
    INDEX
    Explanations

    matchday or round in a league

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    hintText
    -0.79
    啕
    -0.70
     раза
    -0.68
     dimensional
    -0.68
     peas
    -0.67
     cardinal
    -0.66
     disapproved
    -0.66
    ianos
    -0.65
     Chalmers
    -0.64
    袋
    -0.64
    POSITIVE LOGITS
     round
    1.37
     weekend
    1.26
     rounds
    1.24
     Week
    1.24
     Match
    1.14
     match
    1.10
     jornada
    1.09
     giornata
    1.09
    round
    1.07
     Round
    1.06
    Activations Density 0.028%

    No Known Activations