© 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. 102670
    Prev
    Next
    INDEX
    Explanations

    communicate with us or you

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

    AI models and software

    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
     policies
    0.44
    starred
    0.44
    Coverage
    0.44
    policies
    0.44
    ，$
    0.43
    ポリシー
    0.43
     കൂടി
    0.43
    ➩
    0.43
     स्थितियों
    0.41
     سیاست
    0.41
    POSITIVE LOGITS
    дной
    0.50
     retour
    0.49
    ド
    0.48
     strada
    0.47
     ফ্রান্স
    0.47
    リ
    0.47
    думы
    0.47
     achats
    0.46
     avenida
    0.46
    時代の
    0.46
    Activations Density 0.002%

    No Known Activations