© 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. 208433
    Prev
    Next
    INDEX
    Explanations

    institutional and financial interests

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

    medium latte, healthy foods

    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
     шко
    0.46
    窓
    0.46
     все
    0.46
    peter
    0.45
    ене
    0.43
    ंश
    0.43
    ъ
    0.43
    ಲ್ಲಿ
    0.42
     я
    0.42
    rama
    0.42
    POSITIVE LOGITS
     Asha
    0.46
    尟
    0.46
     asymptote
    0.45
     ident
    0.45
    Taylor
    0.45
     দমন
    0.45
     Markdown
    0.45
    Kelly
    0.45
    क्स्ट
    0.44
     rebounds
    0.44
    Activations Density 0.000%

    No Known Activations