© 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
    5. 16-GEMMASCOPE-2-RES-16K
    7. 651
    Prev
    Next
    INDEX
    Explanations

    conversational follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite

    I'll, I am, I will

    np_acts-logits-general · gemini-2.5-flash-lite

    period

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ،
    0.54
     Викто
    0.52
    \
    0.52
     они
    0.51
     روز
    0.50
     Ни
    0.50
     barbers
    0.50
     Ли
    0.49
    <h5>
    0.49
     gliding
    0.48
    POSITIVE LOGITS
    ın
    0.56
    AE
    0.54
    ན་
    0.52
    ュ
    0.52
    서를
    0.50
    า
    0.50
    UATION
    0.49
    ു
    0.49
    PARTMENT
    0.49
    従って
    0.49
    Activations Density 0.001%

    No Known Activations