© 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. 111724
    Prev
    Next
    INDEX
    Explanations

    love it

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

    complicated subjects or tasks

    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
     ي
    0.50
    ЕН
    0.48
    简介
    0.46
    Ε
    0.45
     davranış
    0.44
     Rewrite
    0.44
    认知
    0.43
     Е
    0.42
    ческий
    0.42
     Editar
    0.42
    POSITIVE LOGITS
    jarah
    0.41
    gers
    0.40
    水量
    0.39
     underground
    0.39
    resses
    0.39
    umbled
    0.39
     น้ํา
    0.39
    水中
    0.39
    মিস্ট
    0.39
     vzduchu
    0.38
    Activations Density 0.000%

    No Known Activations