© 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. 85782
    Prev
    Next
    INDEX
    Explanations

    sports officials and game pieces

    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_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
    こともあります
    -1.36
     scolaires
    -1.34
    Páginas
    -1.26
    comme
    -1.20
     ordre
    -1.17
     favoris
    -1.17
    Kindly
    -1.15
     باتری
    -1.15
     abonnement
    -1.15
    孖
    -1.13
    POSITIVE LOGITS
     where
    1.71
     there
    1.44
     from
    1.40
    大部分
    1.23
     when
    1.23
     which
    1.19
     aislada
    1.09
    ménage
    1.09
     although
    1.08
     redonda
    1.06
    Activations Density 0.011%

    No Known Activations