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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179033
    Prev
    Next
    INDEX
    Explanations

    non-English characters or words

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

    potential leverage, divine intervention, faith tradition, Kafka Streams

    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_31_width_262k_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
    रिक्
    0.48
    ėje
    0.47
    ПУ
    0.46
    נק
    0.46
    ುತ್ತಿರುವ
    0.46
    minipage
    0.45
    𝚕
    0.45
    ने
    0.44
    च्युअल
    0.44
    ıcı
    0.44
    POSITIVE LOGITS
     о
    0.59
     ا
    0.48
     عرب
    0.47
     arid
    0.47
     عربي
    0.47
     of
    0.46
    ဖြစ်
    0.46
    のカ
    0.45
     ο
    0.45
     concetto
    0.45
    Activations Density 0.001%

    No Known Activations