© 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. 194463
    Prev
    Next
    INDEX
    Explanations

    being said, calls, inspires, important

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

    configuration and technical terms

    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
    मुळे
    0.52
    yla
    0.50
    к
    0.47
    RIO
    0.45
    的精神
    0.45
     Ajay
    0.43
    кци
    0.42
    atau
    0.42
    ibil
    0.42
     dadurch
    0.41
    POSITIVE LOGITS
     ถ
    0.51
     આગાહી
    0.50
     Шта
    0.48
    队列
    0.47
     तरह
    0.46
     ασ
    0.46
     conjuntos
    0.46
     스타
    0.46
     ভাষা
    0.45
     পরেই
    0.45
    Activations Density 0.000%

    No Known Activations