© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151702
    Prev
    Next
    INDEX
    Explanations

    construction cleaning or holy spirit

    np_acts-logits-general · gemini-2.5-flash-lite

    incoming transport and Cornerstone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bersifat
    0.42
    ৃহ
    0.42
    '
    0.41
     undertakings
    0.41
     undertakes
    0.41
    Largest
    0.40
    Hasta
    0.39
     বছর
    0.39
     timezone
    0.39
     stewards
    0.39
    POSITIVE LOGITS
    uları
    0.50
     亻
    0.49
    YP
    0.48
     لقي
    0.48
     الل
    0.47
    ugía
    0.47
    тувати
    0.47
    ologien
    0.46
    क
    0.46
     Indi
    0.46
    Activations Density 0.003%

    No Known Activations