© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 221940
    Prev
    Next
    INDEX
    Explanations

    legal or formal contexts

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

    Pros, formation, hashing, information

    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
     germinate
    0.51
    特に
    0.51
    滝
    0.48
    그리고
    0.46
    Nw
    0.46
    특히
    0.45
    냇
    0.44
     cyberpunk
    0.44
     দেবযানী
    0.43
    땡
    0.42
    POSITIVE LOGITS
    ka
    0.55
    ega
    0.52
    el
    0.51
    wa
    0.51
    iga
    0.50
     acima
    0.48
    委員會
    0.48
    edo
    0.47
     समिति
    0.47
    orte
    0.47
    Activations Density 0.000%

    No Known Activations