© 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. 35923
    Prev
    Next
    INDEX
    Explanations

    exams, commands, trust, bumping

    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
     форма
    0.60
    ừng
    0.55
     контроль
    0.54
    bring
    0.52
    f
    0.52
    ě
    0.51
     осторо
    0.50
    鴛
    0.49
     الآخر
    0.48
    广东
    0.48
    POSITIVE LOGITS
     computationally
    0.55
     sprouted
    0.55
     an
    0.54
     gracefully
    0.53
     constructed
    0.53
     purchased
    0.52
     cluttered
    0.52
     assays
    0.51
     transceiver
    0.51
     essays
    0.50
    Activations Density 0.000%

    No Known Activations