© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2032
    Prev
    Next
    INDEX
    Explanations

    foreign language words and colons

    np_acts-logits-general · gemini-2.5-flash-lite

    structured data communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
    甬
    0.24
     গি
    0.23
    🕔
    0.23
    㽚
    0.22
    遠慮
    0.22
    気軽
    0.22
     සහිත
    0.21
    ത്തിനു
    0.21
     따로
    0.21
    ('/').
    0.21
    POSITIVE LOGITS
     그런데
    0.25
     finales
    0.22
     Menteri
    0.22
    Phase
    0.21
    سور
    0.21
    erecht
    0.21
    arag
    0.21
    ,”
    0.21
    ,’
    0.21
     Rice
    0.20
    Activations Density 0.120%

    No Known Activations