© 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. 210596
    Prev
    Next
    INDEX
    Explanations

    foreign language university hotel

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

    dependencies can

    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
     (
    0.52
    felt
    0.51
     Δ
    0.51
    0.49
     △
    0.48
    yl
    0.48
     ∆
    0.46
    iri
    0.46
    services
    0.46
    ere
    0.46
    POSITIVE LOGITS
    緑
    0.53
     universidades
    0.51
    淔
    0.50
    ப்பட்ட
    0.50
    㴼
    0.49
     বিশ্ববিদ্যালয়ে
    0.48
     قدیمی
    0.48
    གས་
    0.48
    溁
    0.47
    ホテル
    0.47
    Activations Density 0.009%

    No Known Activations