© 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. 7877
    Prev
    Next
    INDEX
    Explanations

    for a

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

    text is long

    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
    द्वानी
    0.43
    iquant
    0.40
     Pequ
    0.39
     BN
    0.39
    ographique
    0.38
     nahil
    0.38
     Neal
    0.38
    쭐
    0.37
    jub
    0.37
    寻
    0.36
    POSITIVE LOGITS
     rob
    0.37
    যান
    0.36
    eft
    0.36
     razones
    0.36
    硬
    0.36
    اصمة
    0.36
     Gon
    0.35
    /~
    0.35
    etano
    0.35
    Ւ
    0.35
    Activations Density 0.005%

    No Known Activations