© 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. 122486
    Prev
    Next
    INDEX
    Explanations

    page followed by a verb

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

    slot, page, or directly

    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
    degenerate
    0.54
    十五章
    0.52
    atangan
    0.51
     લાભ
    0.50
    尭
    0.50
    場の
    0.49
    adiabatic
    0.49
    skinned
    0.48
    ᱑
    0.47
    ذی
    0.47
    POSITIVE LOGITS
    org
    0.47
    udo
    0.46
    assan
    0.45
     السر
    0.45
     أس
    0.44
     usado
    0.44
    ')
    0.44
    su
    0.44
    Universal
    0.43
     периоди
    0.42
    Activations Density 0.001%

    No Known Activations