© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 898
    Prev
    Next
    INDEX
    Explanations

    Pennsylvania, Philadelphia, Trenton

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kidman
    0.63
     morality
    0.59
    cretion
    0.58
    öl
    0.58
     morals
    0.57
    acak
    0.57
    ensors
    0.56
     اسلامی
    0.56
    钦
    0.55
     Kino
    0.55
    POSITIVE LOGITS
     Chesapeake
    1.46
     Pennsylvania
    1.39
     Philly
    1.37
     SEPT
    1.35
     Drexel
    1.35
     Philadelphia
    1.34
     Delaware
    1.34
     Wilkes
    1.31
    Pennsylvania
    1.29
    Philadelphia
    1.28
    Activations Density 1.654%

    No Known Activations