© 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. 68811
    Prev
    Next
    INDEX
    Explanations

    international topics and experiences

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

    Palestinian regions and specific items

    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
    걔
    0.50
    븅
    0.49
    Gets
    0.45
     hert
    0.45
     값을
    0.44
     आहेत
    0.44
     применяется
    0.44
     הם
    0.43
    çoivent
    0.43
    랬
    0.43
    POSITIVE LOGITS
     جنوبی
    0.54
     unsettling
    0.46
     UNICEF
    0.45
     バー
    0.43
     Palestinian
    0.43
    韓國
    0.42
     haunted
    0.41
     umbrellas
    0.41
    ায়
    0.41
    自殺
    0.41
    Activations Density 0.001%

    No Known Activations