© 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. 195021
    Prev
    Next
    INDEX
    Explanations

    eventually win

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

    by myself and

    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
    ².
    0.49
    sofar
    0.46
    buatan
    0.45
    .*/
    0.45
     min
    0.44
     मिळू
    0.44
    .。
    0.43
     प्रशंस
    0.43
    .*
    0.43
     pointing
    0.43
    POSITIVE LOGITS
    ሎች
    0.44
    oł
    0.44
    ुक्त
    0.44
    ታል
    0.43
    Adder
    0.42
     بيه
    0.42
    ነስ
    0.41
     ইন্দু
    0.41
    纷
    0.41
    动手
    0.40
    Activations Density 0.001%

    No Known Activations