© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35595
    Prev
    Next
    INDEX
    Explanations

    varying ratios levels tones degrees

    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
    b
    1.39
    나
    1.23
    g
    1.17
    다
    1.11
    c
    1.09
    𝘀
    1.00
    습니다
    0.98
    d
    0.97
    t
    0.94
    ش
    0.94
    POSITIVE LOGITS
    1.09
    <0x9E>
    0.91
     on
    0.89
    ’
    0.89
     of
    0.82
     as
    0.81
    '
    0.81
    yla
    0.80
     varying
    0.77
    ร
    0.75
    Activations Density 0.010%

    No Known Activations