© 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. 234729
    Prev
    Next
    INDEX
    Explanations

    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
    c
    0.52
     PROJECT
    0.49
     MILLER
    0.49
     JOURNAL
    0.47
    g
    0.47
     REG
    0.47
    j
    0.46
    b
    0.46
     immobil
    0.45
     clientele
    0.45
    POSITIVE LOGITS
     nye
    0.49
     Paying
    0.47
     nya
    0.46
     ओके
    0.45
    ंजा
    0.45
    陰
    0.44
    不過
    0.44
     وبعد
    0.44
    Ũ
    0.44
    苼
    0.44
    Activations Density 0.001%

    No Known Activations