© 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. 99756
    Prev
    Next
    INDEX
    Explanations

    low hanging fruits

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

    depends on whether

    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
    رب
    0.52
    arens
    0.47
     ald
    0.47
    یس
    0.46
    Ald
    0.45
    犄
    0.45
    خت
    0.45
    ئر
    0.44
    خ
    0.44
    市镇
    0.44
    POSITIVE LOGITS
    াধিক
    0.54
    ໍ
    0.49
     தெளி
    0.47
     paucity
    0.46
     Marlborough
    0.46
     พิจิก
    0.46
     dilapidated
    0.45
     Marlow
    0.45
     受け
    0.44
     فونبټ
    0.44
    Activations Density 0.001%

    No Known Activations