© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85306
    Prev
    Next
    INDEX
    Explanations

    foreign language and code snippets

    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
     we
    -1.91
    -
    -1.78
    ,
    -1.78
     our
    -1.74
     they
    -1.57
     mußten
    -1.55
     of
    -1.48
     małe
    -1.47
     itself
    -1.45
     inconvénients
    -1.45
    POSITIVE LOGITS
     
    1.78
    $}
    1.34
    』『
    1.34
     did
    1.33
     OnInit
    1.30
    geries
    1.28
    onomies
    1.28
     различных
    1.27
     разных
    1.26
    adí
    1.23
    Activations Density 0.014%

    No Known Activations