© 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
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6936
    Prev
    Next
    INDEX
    Explanations

    error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    دد
    1.44
     sacr
    1.36
    的两
    1.31
    緒
    1.30
     Arz
    1.29
     distante
    1.28
    жни
    1.27
    擔
    1.26
     Tz
    1.25
     рук
    1.25
    POSITIVE LOGITS
    elab
    1.36
    nation
    1.35
    kick
    1.33
    KAL
    1.31
     EPL
    1.30
    ebut
    1.29
     '?
    1.26
    chel
    1.26
    onom
    1.23
    Kick
    1.23
    Activations Density 0.000%

    No Known Activations