© 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. 31700
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    code, business, and opinions

    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
    த்தி
    0.35
    ดี๋ยว
    0.34
    ลาส
    0.30
    posición
    0.29
    ங்கம்
    0.29
     شاء
    0.29
    笤
    0.29
     ремо
    0.28
    管道
    0.28
    蕈
    0.28
    POSITIVE LOGITS
    以及
    0.43
     અને
    0.38
     والس
    0.38
     và
    0.37
     и
    0.37
     és
    0.37
     και
    0.36
     এবং
    0.35
    এবং
    0.35
     மற்றும்
    0.34
    Activations Density 0.177%

    No Known Activations