© 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. 116273
    Prev
    Next
    INDEX
    Explanations

    trespassing and intrusion

    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
    .
    0.49
    ationale
    0.46
     newer
    0.46
     lini
    0.46
     Commentaires
    0.46
     bulat
    0.45
    ý
    0.45
     pront
    0.45
     Popul
    0.45
    s
    0.45
    POSITIVE LOGITS
    in
    0.54
    ”。
    0.53
     arterioles
    0.53
    intrusion
    0.51
    ン
    0.50
    रेज
    0.49
    মিক্যাল
    0.49
    i
    0.47
    マー
    0.47
     impairment
    0.46
    Activations Density 0.000%

    No Known Activations