© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    lists and enumerations

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

    listing items followed by etc

    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
    并且
    0.40
    並且
    0.39
    并
    0.36
    那个
    0.34
    媑
    0.32
    ṭ
    0.32
     Instantiate
    0.32
    이고
    0.32
     kawaida
    0.30
    䉿
    0.30
    POSITIVE LOGITS
     എന്നിവ
    0.46
     etc
    0.44
     ஆகியவற்ற
    0.40
     among
    0.40
     amongst
    0.40
    among
    0.40
     തുടങ്ങിയ
    0.39
    etc
    0.38
    といった
    0.38
     ஆகிய
    0.37
    Activations Density 0.644%

    No Known Activations