© 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. 97775
    Prev
    Next
    INDEX
    Explanations

    academic or professional qualifications

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

    Abu Dhabi and diverse entities

    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
    为其
    0.44
    ึ
    0.44
    きました
    0.43
    躏
    0.43
     violently
    0.42
    𝚔
    0.41
    雏
    0.41
    ➋
    0.41
     irreducible
    0.40
    ൂടെ
    0.40
    POSITIVE LOGITS
    合計
    0.47
     المج
    0.45
    handling
    0.45
    standards
    0.45
     حديث
    0.44
     vucc
    0.44
    標準
    0.44
     zestaw
    0.44
     지방
    0.43
     poesia
    0.43
    Activations Density 0.003%

    No Known Activations