© 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. 117510
    Prev
    Next
    INDEX
    Explanations

    percentages of elements

    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
    s
    1.78
    t
    1.42
    ק
    1.35
    ิ
    1.30
    v
    1.28
    ↵↵
    1.27
    r
    1.27
    માં
    1.23
    k
    1.18
    к
    1.13
    POSITIVE LOGITS
    in
    1.56
    as
    1.24
    不
    1.23
    inį
    1.15
    inney
    1.11
    一些
    1.09
    레스
    1.07
    1
    1.06
    শংস
    1.04
    לב
    1.02
    Activations Density 0.018%

    No Known Activations