© 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. 42254
    Prev
    Next
    INDEX
    Explanations

    don't get me wrong

    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
    Bisa
    -1.66
    ※※
    -1.56
    瑒
    -1.48
    Hanya
    -1.45
    珖
    -1.44
     esetén
    -1.43
    unanje
    -1.39
    Fakta
    -1.39
     รส
    -1.39
    ataires
    -1.38
    POSITIVE LOGITS
     about
    2.30
    o
    1.76
    ).
    1.60
    \
    1.53
    (),
    1.49
    O
    1.48
    ′,
    1.45
    ’).
    1.44
     về
    1.42
    ();
    1.41
    Activations Density 0.006%

    No Known Activations