© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9382
    Prev
    Next
    INDEX
    Explanations

    boundary between places

    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
    tyfik
    -1.99
    "{\
    -1.74
    ໌
    -1.65
    kiksi
    -1.63
     kolor
    -1.57
     zapal
    -1.54
     ellos
    -1.51
     znal
    -1.50
     typy
    -1.50
    ଢ
    -1.48
    POSITIVE LOGITS
     of
    1.63
     tuta
    1.46
    ***
    1.34
     turista
    1.34
    有時
    1.31
     zusätzlichen
    1.31
     Especially
    1.30
    —
    1.30
     between
    1.28
    勿論
    1.28
    Activations Density 0.037%

    No Known Activations