© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 219259
    Prev
    Next
    INDEX
    Explanations

    storage container, default settings

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

    seen things, kingdoms, combinations, politics

    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
    illes
    0.44
     pathophysiology
    0.41
    essler
    0.41
     affaires
    0.40
    া
    0.40
     Saal
    0.40
    나가
    0.40
     Disease
    0.39
     espace
    0.38
     Ice
    0.38
    POSITIVE LOGITS
     установлен
    0.50
     идентифика
    0.46
    };
    0.46
     умолчанию
    0.45
    });
    0.43
    現在の
    0.43
    codingPath
    0.42
    	
    0.42
     времени
    0.42
     прибы
    0.41
    Activations Density 0.002%

    No Known Activations