© 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. 48539
    Prev
    Next
    INDEX
    Explanations

    stunned silence

    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
    d
    1.52
    e
    1.46
    t
    1.46
    s
    1.46
    ’
    1.39
    '
    1.30
    j
    1.24
    X
    1.23
    V
    1.16
    p
    1.16
    POSITIVE LOGITS
    ра
    1.24
    ل
    1.05
     ピ
    1.04
     determinadas
    1.04
    रा
    1.02
    ్రా
    1.02
    ம்
    1.01
     مالی
    1.00
     አበባ
    1.00
    ла
    0.99
    Activations Density 0.001%

    No Known Activations