© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3063
    Prev
    Next
    INDEX
    Explanations

    from followed by source

    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_16_width_65k_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
    D
    1.30
    ۰
    1.05
    ០
    1.03
     amiga
    1.02
    in
    1.02
    X
    0.98
    ;
    0.97
    ٠
    0.97
    T
    0.97
    O
    0.95
    POSITIVE LOGITS
    ک
    1.59
    ม
    1.55
    ر
    1.38
    م
    1.38
    r
    1.25
     whence
    1.23
    し
    1.22
    이를
    1.20
    이
    1.11
    트
    1.09
    Activations Density 0.238%

    No Known Activations