© 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. 59870
    Prev
    Next
    INDEX
    Explanations

    some of

    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
     "
    -1.48
    '
    -1.48
    you
    -1.43
     Different
    -1.42
    only
    -1.36
     quieran
    -1.35
    "
    -1.32
     Which
    -1.31
    看了一眼
    -1.31
     The
    -1.30
    POSITIVE LOGITS
     lienzo
    1.43
     princesas
    1.39
     masih
    1.38
    もありますが
    1.34
     escritura
    1.34
     sillas
    1.34
     religiosos
    1.34
     still
    1.31
    číta
    1.31
    kinci
    1.30
    Activations Density 0.006%

    No Known Activations