© 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. 201390
    Prev
    Next
    INDEX
    Explanations

    registered trademarks

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

    Palantir

    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
    ես
    0.47
     unité
    0.46
    рей
    0.45
    ورية
    0.44
    挂
    0.44
    ﻮ
    0.44
    été
    0.44
    ки
    0.43
    芑
    0.43
    也会
    0.43
    POSITIVE LOGITS
     Compre
    0.55
     Tuberculosis
    0.54
     Surname
    0.52
     PROGRESS
    0.52
    DBMS
    0.51
     शक
    0.50
     Microscopy
    0.50
    t
    0.50
     Scope
    0.49
     Supplied
    0.49
    Activations Density 0.000%

    No Known Activations