© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7670
    Prev
    Next
    INDEX
    Explanations

    figure it out

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

    point it out

    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
     한다
    0.39
    GoString
    0.37
     caul
    0.36
     Tutti
    0.36
    pathname
    0.35
     spines
    0.35
    性に
    0.35
    诰
    0.35
    гает
    0.34
     Doing
    0.33
    POSITIVE LOGITS
    ///
    0.43
    acter
    0.40
     bunları
    0.39
     shit
    0.38
    shit
    0.38
     সেগুলি
    0.38
    мір
    0.38
     THEY
    0.38
     මෙය
    0.37
    UniqueIdentifier
    0.37
    Activations Density 0.110%

    No Known Activations