© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6342
    Prev
    Next
    INDEX
    Explanations

    quantization

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     prescriptions
    0.49
     butyl
    0.44
    Мне
    0.44
    疖
    0.43
     boric
    0.41
     francés
    0.41
    elow
    0.41
     दवाओं
    0.41
     Grecia
    0.41
    赤い
    0.40
    POSITIVE LOGITS
    issement
    0.48
    headline
    0.42
     কাপুর
    0.42
     wysoko
    0.41
    予告
    0.40
     redeem
    0.40
    c
    0.40
     చేస్తున్న
    0.39
     تع
    0.38
    fetchone
    0.38
    Activations Density 0.079%

    No Known Activations