© 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. 126465
    Prev
    Next
    INDEX
    Explanations

    Palestinian Authority actions

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

    Arab Palestinian conflict

    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
    Cumulative
    0.46
     marshm
    0.44
     Caste
    0.42
    гада
    0.42
     অন্যায়
    0.42
    岬
    0.42
     prodotto
    0.41
     ट्रैक
    0.41
     дет
    0.41
     Cumulative
    0.41
    POSITIVE LOGITS
    ずに
    0.39
    ってしまう
    0.38
    🏨
    0.38
     scandal
    0.36
    庁
    0.36
    ologne
    0.36
    ()['
    0.36
    增强
    0.35
    rennen
    0.35
    旧
    0.35
    Activations Density 0.026%

    No Known Activations