© 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. 17392
    Prev
    Next
    INDEX
    Explanations

    grow and expand

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

    beyond, inside, expand, contain

    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
     চিঠি
    0.40
     ciudadanía
    0.40
    傷害
    0.39
     ショ
    0.39
     者
    0.39
     स्पष्ट
    0.38
    Selamat
    0.38
     ದ
    0.38
     쇼
    0.38
    引き続き
    0.38
    POSITIVE LOGITS
    galo
    0.44
     naturally
    0.41
    }$.,
    0.40
     lys
    0.40
    akon
    0.38
    と思っています
    0.38
    agon
    0.37
     crystalline
    0.37
     galaxy
    0.37
     Gor
    0.37
    Activations Density 0.000%

    No Known Activations