© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53315
    Prev
    Next
    INDEX
    Explanations

    international consortium

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

    respecting relationships, comic book

    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
    ඔ
    0.54
    ños
    0.47
    .*;
    0.47
     octubre
    0.46
     высоту
    0.46
    他们在
    0.46
    ম্ব
    0.45
    ्रिक
    0.45
    他们的
    0.45
    iknya
    0.45
    POSITIVE LOGITS
     Consortium
    0.45
     المثال
    0.45
     denken
    0.44
    la
    0.44
    鐩
    0.44
     saker
    0.43
     kontinu
    0.42
     definitiv
    0.42
    يمق
    0.42
     continu
    0.42
    Activations Density 0.000%

    No Known Activations