© 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. 111664
    Prev
    Next
    INDEX
    Explanations

    its success

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

    academic or research context

    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
     fø
    0.44
    Necessary
    0.43
     تاز
    0.43
    isiones
    0.42
     Вай
    0.41
     взаимодействия
    0.41
    acyjne
    0.40
     Ҳ
    0.40
    Sic
    0.40
     получение
    0.40
    POSITIVE LOGITS
     kuliah
    0.56
    enk
    0.48
     inflate
    0.47
     baš
    0.46
    čet
    0.46
    ব
    0.46
     kampus
    0.46
     beeinfl
    0.45
     sapon
    0.44
     overcrow
    0.43
    Activations Density 0.000%

    No Known Activations