© 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. 48820
    Prev
    Next
    INDEX
    Explanations

    teaching you received

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

    macOS Homebrew installs

    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
     d
    0.49
     {
    0.46
     renewed
    0.42
     (
    0.42
     l
    0.41
     “
    0.41
     Vanderbilt
    0.40
     B
    0.40
     want
    0.40
     आगामी
    0.39
    POSITIVE LOGITS
    звичай
    0.53
    이지만
    0.49
     nigdy
    0.48
    此之外
    0.48
    ప్‌
    0.47
    бычно
    0.47
    ப்போதும்
    0.47
    ழக
    0.46
    洍
    0.46
    คคล
    0.46
    Activations Density 0.000%

    No Known Activations