© 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. 10-GEMMASCOPE-RES-131K
    7. 60682
    Prev
    Next
    INDEX
    Explanations

    Rhodes, Asia Minor, Crete

    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
    瘓
    -1.62
    躋
    -1.56
    what
    -1.55
    ⌑
    -1.54
     verpflich
    -1.52
    婓
    -1.51
     Vergangenheit
    -1.44
     moeten
    -1.43
    èrement
    -1.43
    the
    -1.43
    POSITIVE LOGITS
     be
    1.75
     любые
    1.73
     любое
    1.35
     카
    1.34
     empre
    1.34
    場は
    1.34
     ane
    1.33
     …
    1.32
    сник
    1.30
    ons
    1.28
    Activations Density 0.011%

    No Known Activations