© 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. 41-GEMMASCOPE-2-RES-262K
    7. 197400
    Prev
    Next
    INDEX
    Explanations

    specific types of documents or concepts

    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_all/layer_41_width_262k_l0_big
    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
    담
    0.47
     olmadığı
    0.41
    证据
    0.41
     fiducia
    0.40
     Margin
    0.39
     episodios
    0.39
    ئن
    0.38
    ട്ടിയ
    0.38
    joints
    0.38
    ంగ్‌
    0.38
    POSITIVE LOGITS
    獣
    0.42
    pronounced
    0.39
    _
    0.37
    ඪ
    0.37
    轍
    0.36
    သွား
    0.36
     शिक्षकों
    0.35
     جاسک
    0.35
    驢
    0.35
    発達
    0.35
    Activations Density 0.682%

    No Known Activations