© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2309
    Prev
    Next
    INDEX
    Explanations

    cycles, emojis, children, directories, culture

    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_13_width_65k_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
    푯
    1.40
    स्रोत
    1.39
    ਜ
    1.38
     caído
    1.37
    덫
    1.37
     진짜
    1.36
    வதும்
    1.36
     måle
    1.35
    측
    1.35
    葢
    1.33
    POSITIVE LOGITS
    𝑖
    1.45
    𝑒
    1.41
    𝑟
    1.36
    𝐵
    1.35
     Opal
    1.32
    ni
    1.27
    number
    1.26
    RootManager
    1.26
     attire
    1.24
    ℎ
    1.23
    Activations Density 0.009%

    No Known Activations