© 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. 62170
    Prev
    Next
    INDEX
    Explanations

    media and foreign characters

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

    signal processing and systems

    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
     ฟ
    0.50
     Amazing
    0.47
     kya
    0.47
     Iya
    0.46
     いや
    0.46
     เลือก
    0.46
    ៈ
    0.46
     เพิ่ม
    0.46
     lista
    0.44
     ஏக்க
    0.44
    POSITIVE LOGITS
    电话
    0.47
    兹
    0.46
    线路
    0.46
     доро
    0.44
    ოდ
    0.44
    （
    0.43
    场
    0.42
    Sire
    0.41
    远
    0.41
    加油
    0.41
    Activations Density 0.000%

    No Known Activations