© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    code utilities and paths

    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
     "
    -1.84
     ("
    -1.64
    ("
    -1.50
     "[
    -1.49
     "@
    -1.43
     ",
    -1.40
     it
    -1.37
     歯科
    -1.32
     ""
    -1.29
     "(
    -1.29
    POSITIVE LOGITS
     verschied
    1.46
    Terug
    1.43
    Didn
    1.43
     avem
    1.42
    ﮨ
    1.40
    Helping
    1.39
     controllare
    1.34
     różnych
    1.34
     forskjellige
    1.32
    capaian
    1.31
    Activations Density 0.024%

    No Known Activations