© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113898
    Prev
    Next
    INDEX
    Explanations

    established sentence structure

    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
     either
    -1.53
    either
    -1.44
     their
    -1.34
    𝖻
    -1.34
     اینکه
    -1.33
    őzés
    -1.33
    この日は
    -1.33
    5
    -1.33
     которы
    -1.32
    Beskrivning
    -1.28
    POSITIVE LOGITS
    куртка
    1.50
     увеличить
    1.41
     Appetit
    1.34
     baut
    1.33
     was
    1.29
    <>
    1.27
    が
    1.25
     открыть
    1.20
     psychologie
    1.20
     into
    1.19
    Activations Density 0.117%

    No Known Activations