© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67849
    Prev
    Next
    INDEX
    Explanations

    header file guards (#ifndef)

    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
    躥
    -1.71
    fordable
    -1.58
    考虑到
    -1.50
    の違い
    -1.48
     maroc
    -1.43
     foon
    -1.41
     zaměst
    -1.41
     austria
    -1.41
    !~
    -1.41
    perature
    -1.40
    POSITIVE LOGITS
    4
    1.75
    </b>
    1.71
    8
    1.65
    2
    1.55
    </h2>
    1.54
    __);
    1.52
    //{
    
    1.51
    ্স
    1.47
    ivable
    1.45
    ).__
    1.45
    Activations Density 0.078%

    No Known Activations