© 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. 73729
    Prev
    Next
    INDEX
    Explanations

    GUI components

    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
    侪
    -1.58
     what
    -1.53
    儀式
    -1.52
    。(
    -1.51
     botol
    -1.48
    😁
    -1.48
    =%
    -1.47
     there
    -1.46
     какой
    -1.45
    😃
    -1.45
    POSITIVE LOGITS
     of
    1.97
     Übersetzungen
    1.45
     เขา
    1.36
    1
    1.34
    8
    1.33
    跟他
    1.30
     already
    1.30
    1.26
    </td>
    1.25
    InputLabel
    1.24
    Activations Density 0.002%

    No Known Activations