© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54205
    Prev
    Next
    INDEX
    Explanations

    electricity generation, normally no, text preservation, ARR projects, boss locations

    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
    šla
    0.41
    懲
    0.40
     pén
    0.39
    了一些
    0.39
    zek
    0.38
     menghad
    0.38
    鋤
    0.38
     విజ
    0.38
    avez
    0.38
    誅
    0.38
    POSITIVE LOGITS
    <0x80>
    0.43
     عادی
    0.41
    的项目
    0.36
     unmodified
    0.36
     sounding
    0.36
    ¿
    0.35
    的全
    0.35
    ományos
    0.35
    եր
    0.35
    发生的
    0.34
    Activations Density 0.001%

    No Known Activations