© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4481
    Prev
    Next
    INDEX
    Explanations

    street addresses

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

    Describes *what*

    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
     কর্মকাণ্ড
    0.44
    kDa
    0.42
    ​.
    0.42
     যেকোনো
    0.41
    ــ
    0.41
    ும்போது
    0.39
    <unused2213>
    0.39
    䋆
    0.39
    icherweise
    0.38
     esports
    0.38
    POSITIVE LOGITS
     বাহিরে
    0.56
    部份
    0.56
     loosing
    0.56
     গ্রহন
    0.55
     изпол
    0.54
     أيض
    0.54
     shew
    0.53
    Callories
    0.51
    साईट
    0.51
    স্‌
    0.51
    Activations Density 0.246%

    No Known Activations