© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21271
    Prev
    Next
    INDEX
    Explanations

    SQL INSERT and LOAD DATA INFILE

    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
     would
    -1.59
     couldn
    -1.53
     vielleicht
    -1.34
     didn
    -1.33
     viata
    -1.27
     biblia
    -1.27
     опять
    -1.27
    ’
    -1.26
    язы
    -1.26
     歳
    -1.26
    POSITIVE LOGITS
     kaplama
    1.35
    datos
    1.33
    沮
    1.29
    鬨
    1.28
    EM
    1.23
    乆
    1.23
    惦
    1.21
    ležit
    1.20
    Verbal
    1.20
    bleiben
    1.18
    Activations Density 0.083%

    No Known Activations