© 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. 34163
    Prev
    Next
    INDEX
    Explanations

    names and logos usage restrictions

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

    no trademark name or logo; no discrimination

    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
    遵守
    0.50
    푼
    0.47
    遵循
    0.42
     соблю
    0.40
     ಮತ್ತು
    0.38
     thereof
    0.38
    दो
    0.38
    呠
    0.38
     developed
    0.37
     it
    0.37
    POSITIVE LOGITS
     имена
    0.51
     маги
    0.46
     Porta
    0.45
     பெயரை
    0.44
    𝒌
    0.44
     एक्ट्रेसेस
    0.44
    主持人
    0.44
     имя
    0.44
     Schild
    0.44
     cổng
    0.43
    Activations Density 0.001%

    No Known Activations