© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136976
    Prev
    Next
    INDEX
    Explanations

    end of sentence contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    എം
    0.45
     hurriedly
    0.45
     atomically
    0.45
    yiz
    0.45
    ፕሮ
    0.44
    ጷ
    0.44
    üs
    0.43
    ন্দ্ব
    0.43
     charmed
    0.43
    ynu
    0.43
    POSITIVE LOGITS
    वला
    0.42
    on
    0.42
    峩
    0.38
    рон
    0.38
    还可以
    0.36
     Trang
    0.36
     necessitate
    0.35
     Turtle
    0.35
    ｍｍ
    0.35
    逺
    0.35
    Activations Density 0.003%

    No Known Activations