© 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. 22-GEMMASCOPE-RES-131K
    7. 66837
    Prev
    Next
    INDEX
    Explanations

    sports events and competitions

    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_22/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
     your
    -1.18
    your
    -1.02
     hacerle
    -0.96
    strual
    -0.94
    toFixed
    -0.94
    ː
    -0.93
     отношению
    -0.93
    claimer
    -0.91
    dienne
    -0.91
     xD
    -0.90
    POSITIVE LOGITS
     garante
    1.12
     ambos
    1.11
     spectacle
    1.11
     espé
    1.07
     envol
    1.05
    双方
    1.05
    ーーーー
    1.04
     vitesses
    1.03
     Francus
    1.02
    ーーー
    1.00
    Activations Density 0.070%

    No Known Activations