© 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. 5145
    Prev
    Next
    INDEX
    Explanations

    specific topics

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

    and, as well as, alike

    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
    性和
    0.47
    かどうか
    0.45
     mesela
    0.38
    ists
    0.37
    OLOGICAL
    0.35
     jeff
    0.35
    ➖➖
    0.35
    벙
    0.35
     iż
    0.34
    力和
    0.34
    POSITIVE LOGITS
     እንዲሁም
    1.13
     serta
    1.02
     alike
    1.00
     ஆகிய
    0.98
     sowie
    0.95
     그리고
    0.95
    といった
    0.93
     ஆகியவற்ற
    0.92
     ஆகியவை
    0.82
    そして
    0.82
    Activations Density 1.136%

    No Known Activations