© 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. 117684
    Prev
    Next
    INDEX
    Explanations

    difference between

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

    steps and ideas

    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
    フジ
    0.49
    Љ
    0.49
     البع
    0.48
     ডিসেম্বর
    0.48
     దూర
    0.46
    感想
    0.45
    表情
    0.44
     タン
    0.44
     Pew
    0.44
    ヨーロッパ
    0.44
    POSITIVE LOGITS
     mãi
    0.46
     scripts
    0.45
    푞
    0.45
     exploits
    0.45
     scandals
    0.45
    까
    0.43
     also
    0.42
     đề
    0.42
     focus
    0.42
     curve
    0.42
    Activations Density 0.000%

    No Known Activations