© 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. 6047
    Prev
    Next
    INDEX
    Explanations

    foreign word beginnings

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

    multiple language phrase beginnings

    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
    five
    0.35
     five
    0.33
    設け
    0.32
    頗
    0.32
     four
    0.31
     {\
    0.31
     சார்பில்
    0.30
     behest
    0.30
     fragmentary
    0.29
     Spanish
    0.29
    POSITIVE LOGITS
     bạn
    0.39
     کنید
    0.39
    اا
    0.39
    스타그램
    0.38
    아요
    0.37
    니다
    0.37
    해요
    0.37
    어요
    0.36
    시간
    0.36
    있
    0.35
    Activations Density 0.051%

    No Known Activations