© 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. 19437
    Prev
    Next
    INDEX
    Explanations

    phrases after "about", "to", "your", "en"

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

    project identifiers

    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
    itabbo
    0.49
    让自己
    0.46
    itabbam
    0.45
    给自己
    0.43
    <unused27>
    0.42
     ውስ
    0.41
     ತೆಗೆದುಕೊಳ್ಳ
    0.41
     prêts
    0.40
    ēng
    0.40
    abhavena
    0.40
    POSITIVE LOGITS
     Candy
    0.48
     Z
    0.46
     Pirate
    0.43
     N
    0.43
     Apache
    0.43
     of
    0.43
     Collaborative
    0.42
     T
    0.42
     pytest
    0.42
     Video
    0.41
    Activations Density 0.001%

    No Known Activations