© 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. 248833
    Prev
    Next
    INDEX
    Explanations

    comprehensive database

    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
    omo
    0.52
    ør
    0.43
     भीम
    0.43
    โน
    0.43
     disparities
    0.43
    匣
    0.42
    ována
    0.42
    คำ
    0.42
    ﻼ
    0.41
    CLC
    0.40
    POSITIVE LOGITS
    et
    0.53
    груп
    0.51
    т
    0.50
     Onun
    0.49
     kurul
    0.48
    ت
    0.48
    я
    0.47
     Ok
    0.47
     Pawar
    0.47
    borders
    0.46
    Activations Density 0.001%

    No Known Activations