© 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. 162197
    Prev
    Next
    INDEX
    Explanations

    foreign or multilingual words

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

    core concepts or personal preferences

    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
    忍
    0.57
    在
    0.54
    Krist
    0.53
    レ
    0.52
    -
    0.52
    電動
    0.51
    の位置
    0.50
    の
    0.50
    生活
    0.50
    忍者
    0.49
    POSITIVE LOGITS
     மற்ற
    0.49
    இதில்
    0.46
     fau
    0.46
     cœur
    0.46
     இனி
    0.46
     Southeastern
    0.45
     Other
    0.45
     diğer
    0.45
     prochain
    0.44
     اقبال
    0.44
    Activations Density 0.000%

    No Known Activations