© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    website links and services

    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
    the
    0.78
    ش
    0.76
    ع
    0.63
    на
    0.59
    ना
    0.55
    ك
    0.54
    that
    0.53
    of
    0.52
    에
    0.52
    ן
    0.52
    POSITIVE LOGITS
     aldehyde
    0.64
    があります
    0.59
    ু
    0.55
    \
    0.53
     oni
    0.53
     fructose
    0.53
     and
    0.52
     dai
    0.52
     jau
    0.52
     incred
    0.52
    Activations Density 0.064%

    No Known Activations