© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 76
    Prev
    Next
    INDEX
    Explanations

    comparing iOS and Android

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Право
    1.10
           
    1.04
     кван
    1.03
     ढाई
    1.02
     río
    0.96
       
    0.96
    䢙
    0.96
         
    0.96
     Förder
    0.95
     liné
    0.95
    POSITIVE LOGITS
     epidermis
    1.13
     predicated
    1.10
     matchmaking
    1.10
     payday
    1.08
     webpages
    1.07
     dilemmas
    1.06
     solamente
    1.03
     safeguards
    1.01
     safegu
    1.01
     discover
    1.00
    Activations Density 1.844%

    No Known Activations