© 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-65K
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    online services and activities

    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_65k_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
    ’”
    1.18
    ’
    1.18
    在
    1.17
    ’)
    1.14
    的
    1.12
    ول
    1.05
    ’),
    1.01
    OfString
    0.99
    𝓵
    0.99
     ຫຼື
    0.99
    POSITIVE LOGITS
    a
    1.79
     a
    1.58
    i
    1.36
    n
    1.33
    it
    1.30
    !
    1.23
    y
    1.22
    ่
    1.21
     the
    1.18
    ?
    1.18
    Activations Density 0.021%

    No Known Activations