© 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. 137117
    Prev
    Next
    INDEX
    Explanations

    job-protected leave, hinder, insulation, drinks, research

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

    . when it Attack

    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
     Genetics
    0.48
    t
    0.47
    ocond
    0.46
     Kira
    0.44
     ११
    0.44
    тих
    0.44
     grundsätzlich
    0.44
    CD
    0.43
     gira
    0.43
    tou
    0.43
    POSITIVE LOGITS
    ક્ત
    0.46
    Substitute
    0.45
     должности
    0.45
    쉴
    0.44
     दिखाया
    0.44
     некоторые
    0.44
    뺨
    0.44
    Vh
    0.43
    ਢ
    0.42
    ור
    0.42
    Activations Density 0.000%

    No Known Activations