© 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. 73586
    Prev
    Next
    INDEX
    Explanations

    connections and communication

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

    questions and answers

    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
     وہی
    0.46
     misdemean
    0.44
     ஏனெ
    0.44
     کھیلنا
    0.42
     വിമ
    0.42
    勳
    0.41
    更是
    0.41
    浪
    0.41
    奠
    0.41
    ព្រ
    0.39
    POSITIVE LOGITS
     actual
    0.50
     will
    0.46
    0
    0.46
    2
    0.46
     observe
    0.45
    awa
    0.45
    ிகு
    0.45
    実際に
    0.44
    ed
    0.44
    ul
    0.43
    Activations Density 0.005%

    No Known Activations