© 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. 31-GEMMASCOPE-2-RES-262K
    7. 118001
    Prev
    Next
    INDEX
    Explanations

    religion, pub, private school

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

    simplifying, future projects, or overcoming resistance

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    to
    0.61
    不
    0.54
    the
    0.52
    your
    0.52
    he
    0.50
    天
    0.50
    past
    0.48
    B
    0.48
    p
    0.47
     terms
    0.47
    POSITIVE LOGITS
     ద
    0.48
     ଯ
    0.48
    msgSender
    0.46
     करिकुलम
    0.46
     কাশি
    0.46
    UWORD
    0.45
     Distortion
    0.44
    척
    0.44
     monotonically
    0.43
     operandSize
    0.43
    Activations Density 0.000%

    No Known Activations