© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111777
    Prev
    Next
    INDEX
    Explanations

    offering / earning / offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝓎
    0.48
    和服务
    0.47
    <unused595>
    0.45
    ೀನ
    0.45
    tDBOutput
    0.44
     እንዲ
    0.44
     말이
    0.44
    ﻴ
    0.44
    𝘺
    0.44
    ぴ
    0.43
    POSITIVE LOGITS
    s
    0.51
    noh
    0.47
    Chronic
    0.46
    ன்னு
    0.46
    Explore
    0.45
    Dealing
    0.45
    Zero
    0.45
     Fiction
    0.45
    var
    0.44
     Developers
    0.44
    Activations Density 0.001%

    No Known Activations