© 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. 201217
    Prev
    Next
    INDEX
    Explanations

    cultivator, brands, replacement, diverse, cravings, providers, Minister

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

    commercial use or project

    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
    s
    0.50
    给
    0.49
     نحو
    0.46
     měst
    0.45
     forward
    0.44
     zá
    0.44
     łat
    0.43
     подрост
    0.43
    へ
    0.43
     snad
    0.42
    POSITIVE LOGITS
     ಸೋ
    0.50
    IRO
    0.49
     cannons
    0.47
     ஆர
    0.46
     பாத
    0.45
     $('
    0.45
     очки
    0.45
     числі
    0.45
    लया
    0.44
    БУ
    0.44
    Activations Density 0.000%

    No Known Activations