© 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. 132704
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific terms

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

    foreign words

    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
    ra
    0.54
    ile
    0.46
    ab
    0.45
    tig
    0.45
    ri
    0.45
    uye
    0.45
    <0x80>
    0.44
    ny
    0.44
    swarm
    0.44
    na
    0.43
    POSITIVE LOGITS
     racemic
    0.46
     ഭക്ഷണം
    0.46
    ्ले
    0.46
     نړ
    0.45
     аромат
    0.45
     партнер
    0.45
     &/
    0.45
    エンス
    0.44
    䛛
    0.44
     پار
    0.44
    Activations Density 0.001%

    No Known Activations