© 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. 90346
    Prev
    Next
    INDEX
    Explanations

    quantitative validation

    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
    ⅝
    -1.55
    ⅜
    -1.45
    ている
    -1.42
    ⅞
    -1.39
    The
    -1.36
     Curiosity
    -1.34
    rigkeit
    -1.33
     Canad
    -1.29
    oneer
    -1.27
     modi
    -1.24
    POSITIVE LOGITS
     between
    1.70
    alucía
    1.41
     recientes
    1.38
     =
    1.36
     antiguas
    1.34
     \
    1.34
    können
    1.31
     habla
    1.26
     fortsetter
    1.25
     menunggu
    1.24
    Activations Density 0.182%

    No Known Activations