© 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. 158743
    Prev
    Next
    INDEX
    Explanations

    only

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

    Important disclaimer

    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
    その他の
    0.52
     могу
    0.44
    ธุ
    0.44
    その他
    0.42
    Pascal
    0.41
    ದಿ
    0.41
    🖉
    0.41
    思
    0.40
     пожела
    0.40
    틸
    0.39
    POSITIVE LOGITS
     ONLY
    0.69
     THIS
    0.55
     only
    0.54
     Finance
    0.54
     Only
    0.54
     downloadable
    0.52
     chỉ
    0.51
     толькі
    0.51
    ONLY
    0.50
     फक्त
    0.50
    Activations Density 0.056%

    No Known Activations