© 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. 115175
    Prev
    Next
    INDEX
    Explanations

    business trips José option extensive research right setting

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

    Clinically, Sustainability Report, square root, explore the

    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
    seer
    0.54
     Работа
    0.53
    
    0.52
    zer
    0.50
     Например
    0.50
    Мы
    0.50
    ring
    0.50
     Тогда
    0.49
    ᱓
    0.49
    }}}
    0.49
    POSITIVE LOGITS
     vin
    0.48
    ادار
    0.48
     tenement
    0.46
     déb
    0.46
     heredity
    0.46
     nanof
    0.46
     terapeut
    0.45
     liquidate
    0.44
     vine
    0.43
     chromatin
    0.43
    Activations Density 0.000%

    No Known Activations