© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27808
    Prev
    Next
    INDEX
    Explanations

    class definitions and types

    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_40_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
    覬
    0.39
    “,
    0.38
     करत
    0.38
    ्रा
    0.37
     γιατί
    0.36
    てる
    0.36
    有關
    0.35
     geführt
    0.35
     కలిసి
    0.35
    ．
    0.35
    POSITIVE LOGITS
     my
    0.63
     d
    0.47
     your
    0.47
     representative
    0.45
     meu
    0.44
     q
    0.44
     Ма
    0.44
     nbsp
    0.42
     browser
    0.41
     _;
    0.41
    Activations Density 0.008%

    No Known Activations