© 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. 6893
    Prev
    Next
    INDEX
    Explanations

    itinerary generation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     teniendo
    1.34
     commencing
    1.32
     Ouv
    1.29
    する場合は
    1.29
    莞
    1.28
     Vieux
    1.28
     actors
    1.28
     ime
    1.26
    繇
    1.25
     xã
    1.20
    POSITIVE LOGITS
    %%
    1.11
    너지
    1.08
     commandant
    1.08
    충
    1.07
    ρης
    1.05
    너
    1.05
     endregion
    1.04
    itrile
    1.03
    臺
    1.02
     Commandant
    1.01
    Activations Density 0.015%

    No Known Activations