© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44962
    Prev
    Next
    INDEX
    Explanations

    output related to code

    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
    of
    -2.64
    褔
    -2.44
    俛
    -2.31
     inteligen
    -2.30
     textu
    -2.28
     and
    -2.27
     hran
    -2.25
     aquí
    -2.23
    瑀
    -2.23
     descub
    -2.22
    POSITIVE LOGITS
    In
    3.08
    緜
    2.97
    ated
    2.94
    7
    2.83
    亊
    2.67
    也沒
    2.55
    4
    2.53
     για
    2.52
     untuk
    2.50
    d
    2.50
    Activations Density 0.019%

    No Known Activations