© 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. 10492
    Prev
    Next
    INDEX
    Explanations

    specific content and its relationships

    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
     bila
    1.02
     itp
    0.97
     więc
    0.95
    ようです
    0.95
    놔
    0.94
     tentativa
    0.94
     ficou
    0.92
    북도
    0.92
     allora
    0.92
    ToObject
    0.92
    POSITIVE LOGITS
    의
    2.40
    の
    2.25
    的
    2.23
    的這個
    2.20
    的的
    2.18
     olan
    2.11
    のア
    2.05
    的全
    2.04
    のマ
    1.96
    的国家
    1.96
    Activations Density 0.015%

    No Known Activations