© 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. 4636
    Prev
    Next
    INDEX
    Explanations

    quality, state, or abstract concept

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

    policy matters and judgements about items

    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
     खरेदी
    0.48
     পর্যাপ্ত
    0.47
     moglie
    0.46
     gonflement
    0.46
     अनुरोध
    0.45
     सॉरी
    0.45
    辣椒
    0.45
    锶
    0.44
     পলিপ
    0.44
    デフォルト
    0.44
    POSITIVE LOGITS
    㥆
    0.44
     worldwide
    0.42
     –
    0.41
    enski
    0.41
     o
    0.39
     effortlessly
    0.39
     &
    0.38
     designed
    0.38
     seamlessly
    0.38
    </em>
    0.37
    Activations Density 0.843%

    No Known Activations