© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    lose my, could feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     fondness
    1.50
     medals
    1.48
     medal
    1.47
     Medal
    1.46
     revenge
    1.46
     immortal
    1.46
     savior
    1.41
    Tunes
    1.37
     \*
    1.37
     Lulu
    1.36
    POSITIVE LOGITS
    дки
    1.37
     dotyczące
    1.32
     распространен
    1.32
    мили
    1.29
     characterizing
    1.28
    aceous
    1.26
    мни
    1.25
    まえ
    1.22
    ண்ணாம
    1.22
    adece
    1.21
    Activations Density 0.101%

    No Known Activations