© 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. 3786
    Prev
    Next
    INDEX
    Explanations

    safety guidelines, malicious purposes

    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
    Negative Logits
     get
    0.67
     “
    0.63
     gets
    0.60
     a
    0.60
     create
    0.55
     "
    0.55
     the
    0.53
     home
    0.53
     important
    0.52
     resource
    0.52
    POSITIVE LOGITS
    ério
    0.57
    utiliser
    0.57
     आचार्य
    0.56
     नाबालिग
    0.55
    prüfung
    0.55
    édération
    0.53
    魈
    0.53
    שי
    0.52
    är
    0.52
    🔞
    0.52
    Activations Density 2.677%

    No Known Activations