© 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. 144747
    Prev
    Next
    INDEX
    Explanations

    image or body parts

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

    help for progress

    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
    5
    0.61
    IT
    0.58
    EN
    0.57
    HR
    0.57
    G
    0.56
    B
    0.55
    PR
    0.54
    4
    0.54
    H
    0.53
    LE
    0.52
    POSITIVE LOGITS
     آتا
    0.49
     الوس
    0.49
     آنا
    0.48
     உள
    0.48
    ၊
    0.48
     дорога
    0.47
     වැඩ
    0.47
     മറ്റൊരു
    0.47
    蒎
    0.47
     prefque
    0.46
    Activations Density 0.000%

    No Known Activations