© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30229
    Prev
    Next
    INDEX
    Explanations

    rapidly impart, its respective

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

    Disco Elysium, flakes for heat, depending on

    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
     ब्रि
    0.49
     використання
    0.46
     Bachelor
    0.45
     अनुवाद
    0.45
     chloroform
    0.44
     ມີ
    0.44
     मासूम
    0.44
    訸
    0.44
     উর্দু
    0.44
     شر
    0.44
    POSITIVE LOGITS
    进度
    0.55
    كره
    0.50
    raints
    0.48
    èn
    0.46
    िंग
    0.45
    쁩
    0.44
    ルート
    0.44
    ժ
    0.43
    ﻛ
    0.43
     about
    0.43
    Activations Density 0.000%

    No Known Activations