© 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. 139162
    Prev
    Next
    INDEX
    Explanations

    snug fit

    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
    ة
    1.19
    ี
    1.09
    ى
    1.09
    ing
    1.05
    k
    1.00
    ı
    0.99
    -
    0.88
    b
    0.87
    ب
    0.82
    w
    0.80
    POSITIVE LOGITS
     as
    1.32
    ل
    1.13
     to
    1.05
     ۹
    1.03
     snug
    1.02
     ח
    0.97
     ג
    0.94
    fY
    0.94
     ﺍﻟ
    0.94
    ۹
    0.94
    Activations Density 0.002%

    No Known Activations