© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6730
    Prev
    Next
    INDEX
    Explanations

    African dragons

    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_22_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
     kişi
    1.07
     Bereiche
    1.01
     場所
    0.99
     особа
    0.98
     Оно
    0.98
     osoba
    0.97
    亽
    0.94
     Nó
    0.92
     Teilnehmer
    0.92
     लड़का
    0.91
    POSITIVE LOGITS
     yellows
    1.47
     browns
    1.38
     Asians
    1.37
     reds
    1.35
     sulfates
    1.33
     miRNAs
    1.32
     whites
    1.32
     oaks
    1.30
     grenades
    1.30
     estrogens
    1.29
    Activations Density 0.993%

    No Known Activations