© 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. 35621
    Prev
    Next
    INDEX
    Explanations

    column description

    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
     MCC
    0.57
    ي
    0.55
     więks
    0.55
     dépôt
    0.55
     uncovering
    0.54
     PTI
    0.54
     maggiori
    0.53
     portraying
    0.53
     altre
    0.52
     szpital
    0.52
    POSITIVE LOGITS
    {
    0.49
    Forgot
    0.47
    hend
    0.44
    Oc
    0.43
    しかし
    0.42
    igation
    0.41
    Escolh
    0.41
    $
    0.41
     dish
    0.40
    Child
    0.40
    Activations Density 0.000%

    No Known Activations