© 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. 32695
    Prev
    Next
    INDEX
    Explanations

    city, teens, gallery

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

    Crimea surge

    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
    主
    0.52
    Ду
    0.49
    สัก
    0.49
     productor
    0.46
     imaged
    0.46
    棹
    0.46
    くだ
    0.45
    ญา
    0.45
    работа
    0.44
    Да
    0.44
    POSITIVE LOGITS
    arez
    0.45
     Athletes
    0.44
     على
    0.44
     عليكم
    0.43
     లక్ష
    0.43
    unlist
    0.43
     gelişmeler
    0.43
     geli
    0.42
     אני
    0.42
    প্রিল
    0.41
    Activations Density 0.000%

    No Known Activations