© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10170
    Prev
    Next
    INDEX
    Explanations

    physical activity, visual studio

    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
    由
    1.55
    已
    1.40
    被
    1.28
    名为
    1.22
    之
    1.21
    或
    1.19
    获
    1.18
    次
    1.18
    以
    1.18
    为
    1.17
    POSITIVE LOGITS
     hehe
    1.93
     hahaha
    1.57
     nowadays
    1.52
     haha
    1.48
     quite
    1.36
     เยอะ
    1.36
     popularized
    1.35
     basically
    1.34
     ㅎㅎ
    1.34
     elaborated
    1.30
    Activations Density 0.003%

    No Known Activations