© 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. 240509
    Prev
    Next
    INDEX
    Explanations

    travel from Ireland

    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
    力的
    0.45
    湡
    0.45
     Mai
    0.44
     Dolomites
    0.44
     Sø
    0.43
    heben
    0.43
     Dre
    0.43
    绝
    0.42
     Medications
    0.42
     Tân
    0.42
    POSITIVE LOGITS
    ిక
    0.48
    ージ
    0.46
     ล่ะ
    0.45
    mbr
    0.45
     மெட்ரோ
    0.45
    の一つ
    0.44
    '>";
    0.44
    চিত্র
    0.44
     gyr
    0.43
    learning
    0.43
    Activations Density 0.001%

    No Known Activations