© 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. 149284
    Prev
    Next
    INDEX
    Explanations

    legal, financial, and academic contexts

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

    technical, code, and descriptive terms

    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
     શક્ય
    0.48
    좁
    0.46
    เข้าร
    0.45
    ೇವ
    0.45
     層
    0.44
    bride
    0.44
     avalanche
    0.44
    ക്കായി
    0.43
     ఉత్త
    0.43
     प्रकरण
    0.43
    POSITIVE LOGITS
    س
    0.49
    ه‌
    0.45
     court
    0.44
     Shakespeare
    0.44
    ўся
    0.43
     Hamilton
    0.43
     whereupon
    0.43
     where
    0.42
    ول
    0.42
     rhet
    0.42
    Activations Density 0.001%

    No Known Activations