© 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. 20938
    Prev
    Next
    INDEX
    Explanations

    please log in

    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
     
    -1.92
     -
    -1.70
     “
    -1.66
    </h1>
    -1.54
     "..\..\..\
    -1.53
    K
    -1.52
     ehemalige
    -1.50
    =“
    -1.50
     многих
    -1.50
     (“
    -1.50
    POSITIVE LOGITS
     Vainqueur
    1.91
     impresa
    1.77
     lamenta
    1.76
     the
    1.70
     這
    1.66
    ⧠
    1.66
    彞
    1.64
     privacidade
    1.61
    Ꮂ
    1.58
    ޞ
    1.58
    Activations Density 0.001%

    No Known Activations