© 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. 604
    Prev
    Next
    INDEX
    Explanations

    model's turn starts

    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
     हिन्दी
    1.31
     ITV
    1.19
     ILO
    1.16
     Hannover
    1.15
     NHT
    1.15
    멕
    1.14
     Hitchcock
    1.13
    Popover
    1.12
     हिंदी
    1.11
     영어
    1.09
    POSITIVE LOGITS
     cultivators
    1.37
     cultivator
    1.36
     cultivation
    1.24
    强者
    1.19
     Martial
    1.18
    修士
    1.17
    仙
    1.17
     Dao
    1.17
    修为
    1.16
     Xuan
    1.16
    Activations Density 0.252%

    No Known Activations