© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    puree, paste, mulch, ketchup, porridge

    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
     any
    -1.83
     "..\..\..\
    -1.68
    ve
    -1.63
    ti
    -1.57
    大多
    -1.57
    š
    -1.50
    ":"+
    -1.50
    䉴
    -1.49
     makinesi
    -1.48
     Hopefully
    -1.48
    POSITIVE LOGITS
    '
    1.83
    ...
    1.61
    '...
    1.58
    pisah
    1.58
    kembang
    1.54
    ...(
    1.48
    ',
    1.47
    <
    1.45
    。"
    1.45
    螄
    1.44
    Activations Density 0.004%

    No Known Activations