© 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. 81047
    Prev
    Next
    INDEX
    Explanations

    specifically disclaims

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

    analyze texts

    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
     সংখ্যাগরিষ্ঠ
    0.59
    ವು
    0.50
     Тихо
    0.50
     мали
    0.49
     сне
    0.47
     рок
    0.47
     цере
    0.45
    〝
    0.43
     ফরজ
    0.43
     Pacífico
    0.43
    POSITIVE LOGITS
     estudos
    0.50
     export
    0.49
    perti
    0.48
     appellate
    0.47
    ARGS
    0.47
    labs
    0.45
    kannya
    0.45
    levant
    0.44
    pos
    0.43
     angular
    0.43
    Activations Density 0.000%

    No Known Activations