© 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. 197575
    Prev
    Next
    INDEX
    Explanations

    popular titles

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

    key logger

    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
    عار
    0.46
    我会
    0.46
    توى
    0.45
     Lily
    0.45
    哑
    0.45
    MouseEnter
    0.45
     grinned
    0.45
    狈
    0.44
     كر
    0.44
     Marlene
    0.43
    POSITIVE LOGITS
    ו
    0.60
     마
    0.56
    ೭
    0.47
     objeto
    0.47
    กว่า
    0.46
    가의
    0.46
     권
    0.46
     DEVICE
    0.45
     conclusive
    0.45
     국내
    0.45
    Activations Density 0.001%

    No Known Activations