© 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. 238899
    Prev
    Next
    INDEX
    Explanations

    known fact

    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
    ュー
    0.45
     ฝึก
    0.45
     WHAT
    0.44
     preparedness
    0.44
    li
    0.44
     $-$
    0.44
     heavenly
    0.43
     valmist
    0.43
     संग्रहीत
    0.43
    ilgan
    0.43
    POSITIVE LOGITS
    每一個
    0.50
    难度
    0.48
    ковых
    0.48
    不好
    0.46
    рати
    0.45
    ংক
    0.45
    耶稣
    0.45
    氧
    0.45
    мым
    0.44
    ζο
    0.44
    Activations Density 0.001%

    No Known Activations