© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25073
    Prev
    Next
    INDEX
    Explanations

    must, essential, obligation

    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_all/layer_41_width_262k_l0_big
    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
     distinct
    0.44
     distinctly
    0.42
     reintroduced
    0.41
    鹑
    0.39
     separately
    0.39
     fibers
    0.39
     perpendicularly
    0.38
     Barre
    0.38
     specifically
    0.38
    distinct
    0.38
    POSITIVE LOGITS
    -
    0.53
    必
    0.50
     obowią
    0.49
    MUST
    0.46
     obligación
    0.46
    Must
    0.46
     Must
    0.45
    !.
    0.44
     imprescindible
    0.44
    read
    0.44
    Activations Density 0.001%

    No Known Activations