© 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. 201202
    Prev
    Next
    INDEX
    Explanations

    limited exceptions

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

    run, analyzed, your, become, represent, honest, is

    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
    broken
    0.43
    冰
    0.41
    হ
    0.41
    蜀
    0.41
    Ice
    0.41
     glistening
    0.41
    블
    0.41
     点击
    0.40
     벗
    0.40
     সৃষ্ট
    0.39
    POSITIVE LOGITS
    
    0.50
     финан
    0.49
     macroeconomic
    0.48
     salariés
    0.47
     hautes
    0.47
     harbours
    0.47
     ವಿಧಾನಸಭಾ
    0.46
    жнарод
    0.46
    歳の
    0.46
     contingencies
    0.45
    Activations Density 0.002%

    No Known Activations