© 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. 58484
    Prev
    Next
    INDEX
    Explanations

    our article, world, Delaware, other, portrait, house portrait

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

    foreign words and prefixes

    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
    afar
    0.48
     lev
    0.48
     aluno
    0.48
     ondul
    0.47
    ટ
    0.47
     ovar
    0.46
     aqu
    0.45
    ετε
    0.45
    來
    0.44
     salwar
    0.44
    POSITIVE LOGITS
     Stamps
    0.51
     تی
    0.48
     فی
    0.46
    ρίζ
    0.46
     تاک
    0.45
    prest
    0.44
     گیرد
    0.42
     φι
    0.42
    แข็ง
    0.41
     کوئی
    0.41
    Activations Density 0.000%

    No Known Activations