© 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. 57013
    Prev
    Next
    INDEX
    Explanations

    following common words

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

    keys, offensive, labor

    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
     เพิ่ม
    0.66
     ทั้ง
    0.49
     elér
    0.49
     他
    0.48
     Bảo
    0.48
     गुप्त
    0.48
     solicitor
    0.48
    शिला
    0.47
     aby
    0.47
     เอง
    0.47
    POSITIVE LOGITS
    odium
    0.48
    bright
    0.47
    which
    0.46
    ოველ
    0.45
    {
    0.45
    that
    0.44
    unique
    0.44
    colorful
    0.44
    define
    0.44
     decimated
    0.43
    Activations Density 0.000%

    No Known Activations