© 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-262K
    7. 16392
    Prev
    Next
    INDEX
    Explanations

    results, Time, signals, allowing, instructions, Spirit, a

    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_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
    ↵
    1.59
     for
    1.40
    5
    1.10
    for
    1.09
    на
    1.03
    4
    0.98
    ન
    0.94
    8
    0.91
    પ
    0.90
    РА
    0.88
    POSITIVE LOGITS
    0.82
    t
    0.76
     It
    0.75
    㑓
    0.74
    ä
    0.72
    í
    0.71
     is
    0.71
    á
    0.69
     {/*
    0.68
     (
    0.66
    Activations Density 0.043%

    No Known Activations