© 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. 222306
    Prev
    Next
    INDEX
    Explanations

    comfort and happiness

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

    attractive japanese

    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
    禮
    0.45
     May
    0.45
    仴
    0.43
     Saves
    0.42
    廢
    0.41
    的這個
    0.40
    พัฒนา
    0.40
    ্টি
    0.40
    
    0.40
     más
    0.40
    POSITIVE LOGITS
     divergents
    0.54
     całkow
    0.48
     எட்டு
    0.48
     uncomplicated
    0.47
     özellik
    0.47
    とおり
    0.46
     ఉంటుంది
    0.46
     tenets
    0.46
     лицом
    0.46
     длина
    0.46
    Activations Density 0.001%

    No Known Activations