© 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. 165287
    Prev
    Next
    INDEX
    Explanations

    to participate

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

    Option or window

    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
    ِر
    0.52
    ندية
    0.50
    ین
    0.49
     sezione
    0.48
     hizo
    0.48
    বিষ্ট
    0.48
    <0x80>
    0.46
     liquido
    0.46
    ﻤ
    0.46
     nome
    0.45
    POSITIVE LOGITS
     आह्वान
    0.48
    éről
    0.46
    ual
    0.45
    ativ
    0.45
     짜
    0.45
    👳
    0.44
    ಾದರೂ
    0.44
    యితే
    0.44
     освіти
    0.44
     выполнить
    0.44
    Activations Density 0.001%

    No Known Activations