© 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. 44151
    Prev
    Next
    INDEX
    Explanations

    angst, IDEA, Lillian

    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
     малень
    -2.53
    の良い
    -2.41
    狁
    -2.34
     הם
    -2.33
     lección
    -2.23
    鳏
    -2.19
     
    -2.13
    Ꭳ
    -2.09
    ⢮
    -2.08
     mereka
    -2.06
    POSITIVE LOGITS
    '
    3.34
     are
    3.06
    は
    2.78
    に
    2.69
    呿
    2.64
     случаях
    2.34
    which
    2.30
    是
    2.27
            
    2.20
    $
    2.19
    Activations Density 0.011%

    No Known Activations