© 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. 198223
    Prev
    Next
    INDEX
    Explanations

    legally copied, create revenue

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

    legal policies thriving

    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
     reorgan
    0.52
     deducting
    0.50
    ሠ
    0.50
     plenary
    0.49
     locksmith
    0.48
     plumbers
    0.48
     americ
    0.47
     kindly
    0.47
    pèce
    0.47
    plicit
    0.47
    POSITIVE LOGITS
    ė
    0.57
    ίο
    0.45
    ação
    0.44
    الإ
    0.44
    ுகளை
    0.43
    语
    0.42
    
    0.42
     caráter
    0.42
    旱
    0.42
     características
    0.42
    Activations Density 0.000%

    No Known Activations