© 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. 248153
    Prev
    Next
    INDEX
    Explanations

    lost...have, divide...between, inherited...my

    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
    ತಕ್ಕ
    0.46
     dico
    0.45
    硏
    0.43
    і
    0.42
    acijama
    0.42
     modestly
    0.41
    пси
    0.41
     sweaty
    0.40
     virtuales
    0.40
     thấp
    0.40
    POSITIVE LOGITS
     调用
    0.49
     Ibid
    0.49
     வி
    0.48
    ={\
    0.48
    érêt
    0.48
    cumin
    0.48
    ।
    0.48
    şim
    0.47
    MIDDLE
    0.47
    USDA
    0.47
    Activations Density 0.000%

    No Known Activations