© 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. 106587
    Prev
    Next
    INDEX
    Explanations

    channel morphology and capacity

    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
    ,
    0.76
     en
    0.66
     are
    0.62
    k
    0.61
     is
    0.60
    .
    0.57
    াকিস্ত
    0.56
     ARMY
    0.56
     (
    0.55
     were
    0.55
    POSITIVE LOGITS
     Спорттук
    0.64
     Два
    0.59
     ત્રણ
    0.59
    asitriangular
    0.59
     பத்து
    0.59
    boxed
    0.58
     ಎರಡು
    0.58
     اجيب
    0.58
    íb
    0.58
     ಯಾವುದೇ
    0.57
    Activations Density 0.002%

    No Known Activations