© 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. 248281
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

    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
    ﻴ
    0.54
    开关
    0.52
    گیر
    0.50
    ००
    0.49
    خی
    0.49
    مانی
    0.48
    才可以
    0.48
    电视
    0.47
    テレビ
    0.46
    ד
    0.46
    POSITIVE LOGITS
     risking
    0.49
     ;\
    0.49
     tanned
    0.49
     Luis
    0.49
    nes
    0.48
     sieben
    0.47
     visibility
    0.47
     illuminates
    0.47
     Luís
    0.47
     anxious
    0.46
    Activations Density 0.000%

    No Known Activations