© 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. 22-GEMMASCOPE-RES-131K
    7. 15117
    Prev
    Next
    INDEX
    Explanations

    such as material types

    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
     pacient
    -0.92
    RILL
    -0.91
    ÇA
    -0.89
    각주
    -0.89
     refriger
    -0.88
     MATHEMATICAL
    -0.88
    ⅙
    -0.88
     Bater
    -0.87
     Bintang
    -0.87
     concess
    -0.86
    POSITIVE LOGITS
     such
    2.48
     including
    1.80
    例如
    1.36
     important
    1.31
     včetně
    1.30
    including
    1.29
    例えば
    1.27
    such
    1.27
     ranging
    1.23
     importantes
    1.23
    Activations Density 0.195%

    No Known Activations