© 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. 181137
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

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

    technical account management

    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
    нкү
    0.55
    летка
    0.48
    лись
    0.47
    湯
    0.47
    क्रो
    0.47
    美味しい
    0.46
    ్రీన్
    0.46
     saludable
    0.46
    চে
    0.45
    捨
    0.45
    POSITIVE LOGITS
     not
    0.53
     THAT
    0.50
     عنا
    0.49
    not
    0.49
     غير
    0.49
     Not
    0.48
    THAT
    0.46
    ORT
    0.46
     שלא
    0.46
    FARE
    0.46
    Activations Density 0.001%

    No Known Activations