© 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. 107247
    Prev
    Next
    INDEX
    Explanations

    subject triangle duck

    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
    Negative Logits
    ahas
    0.49
    ľa
    0.49
    eer
    0.48
    adies
    0.47
     다르
    0.45
    াস্থ্য
    0.45
     料
    0.45
    urred
    0.44
     Hesap
    0.44
     கொண்டாட
    0.44
    POSITIVE LOGITS
    ן
    0.60
    ش
    0.58
    ש
    0.55
    ный
    0.54
    نس
    0.52
    জ
    0.52
    ز
    0.52
    כ
    0.52
    یت
    0.50
    یک
    0.49
    Activations Density 0.000%

    No Known Activations