© 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. 71084
    Prev
    Next
    INDEX
    Explanations

    Category listings

    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
     paradigma
    -1.40
     emblema
    -1.39
    它们
    -1.30
     turista
    -1.28
     ingrediente
    -1.28
     complemento
    -1.27
     contenta
    -1.27
     tirada
    -1.25
     suci
    -1.21
     they
    -1.20
    POSITIVE LOGITS
     различ
    1.41
     различные
    1.32
     мужская
    1.29
     EIGHT
    1.28
     çeşitli
    1.27
     nuevamente
    1.27
     mehrerer
    1.27
     огромное
    1.26
     öff
    1.23
     diversos
    1.23
    Activations Density 0.000%

    No Known Activations