© 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. 631
    Prev
    Next
    INDEX
    Explanations

    reporting findings

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

    implies/indicates followed by consequence/explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    0.84
     of
    0.70
     at
    0.64
     was
    0.64
     is
    0.63
    of
    0.63
     i
    0.60
    are
    0.57
     wenn
    0.55
     are
    0.55
    POSITIVE LOGITS
    N
    0.50
    ת
    0.46
    B
    0.41
    ין
    0.41
    T
    0.39
    Peach
    0.38
    Z
    0.37
     nonconvex
    0.37
    다고
    0.36
    핍
    0.36
    Activations Density 5.908%

    No Known Activations