© 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. 49362
    Prev
    Next
    INDEX
    Explanations

    word beginnings and continuations

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

    I'm Gemma

    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
    ט
    0.53
    uch
    0.52
    pt
    0.50
    ut
    0.49
    and
    0.49
    ell
    0.47
    лі
    0.47
    will
    0.46
    uk
    0.46
    2
    0.45
    POSITIVE LOGITS
     complicado
    0.44
     pesky
    0.44
     yank
    0.43
    ప్‌
    0.43
     gotta
    0.42
     baš
    0.42
     “[
    0.41
     widen
    0.41
     wacky
    0.41
     relaunch
    0.41
    Activations Density 0.055%

    No Known Activations