© 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. 154543
    Prev
    Next
    INDEX
    Explanations

    travel documents or USA

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

    AI models and learning help

    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
    <0xE8>
    0.46
    il
    0.45
    <0xE6>
    0.44
    лению
    0.44
    adka
    0.44
    æ
    0.44
    ay
    0.43
    攵
    0.43
    В
    0.43
    ма
    0.43
    POSITIVE LOGITS
     nhưng
    0.50
     usa
    0.50
     nessuna
    0.50
     USA
    0.50
     cca
    0.49
     jantung
    0.49
     αλλά
    0.48
     memasuki
    0.47
     taur
    0.47
     viable
    0.47
    Activations Density 0.000%

    No Known Activations