© 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. 66019
    Prev
    Next
    INDEX
    Explanations

    Slovak, Polish, Spanish, Portuguese, Japanese words

    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
    -
    -1.73
     of
    -1.70
    {
    -1.64
    '
    -1.64
     verhind
    -1.51
     (
    -1.50
     gets
    -1.47
     tends
    -1.45
     one
    -1.45
    /
    -1.44
    POSITIVE LOGITS
    葙
    1.65
    tych
    1.56
     nazwis
    1.53
     Slovensku
    1.45
     Condiciones
    1.43
    quely
    1.42
    CurtirCurtir
    1.41
    FOREWORD
    1.40
     longterm
    1.40
    時も
    1.39
    Activations Density 0.017%

    No Known Activations