© 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. 123681
    Prev
    Next
    INDEX
    Explanations

    Audrey Aubrey Andrey

    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
    ing
    -2.94
     ''
    -2.92
     принцип
    -2.83
     '
    -2.80
    \
    -2.59
     -
    -2.36
    v
    -2.34
    ".
    -2.34
    ('
    -2.33
     ,
    -2.31
    POSITIVE LOGITS
    苾
    2.63
    The
    2.58
    dáms
    2.48
    ſche
    2.47
     моя
    2.39
    ߺ
    2.39
     hunne
    2.38
    罴
    2.34
    彀
    2.34
    gegevens
    2.34
    Activations Density 0.001%

    No Known Activations