© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85028
    Prev
    Next
    INDEX
    Explanations

    literary collections and books

    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
     temporaire
    -1.35
     palsu
    -1.34
    brie
    -1.31
    вить
    -1.30
    所の
    -1.27
    rů
    -1.27
    mittelt
    -1.26
    IEN
    -1.24
    Annotated
    -1.23
     kimdir
    -1.23
    POSITIVE LOGITS
     is
    1.46
     carácter
    1.41
     if
    1.41
     If
    1.33
    ):
    1.33
    COMO
    1.21
    !)
    1.21
     that
    1.20
     erklärt
    1.20
    asjon
    1.20
    Activations Density 0.048%

    No Known Activations