© 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. 137852
    Prev
    Next
    INDEX
    Explanations

    time at

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

    explaining value or how

    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
     Corrosion
    0.44
     ପ
    0.43
     Koran
    0.42
     зру
    0.42
    izzato
    0.41
     Afric
    0.41
     Cou
    0.41
     рік
    0.41
     Corne
    0.41
     catching
    0.40
    POSITIVE LOGITS
    ంతరం
    0.46
    惴
    0.46
    िटेशन
    0.45
    女士
    0.45
    лкой
    0.43
    Вакансия
    0.43
    etheless
    0.42
     essencial
    0.42
    ర్టు
    0.42
    债
    0.42
    Activations Density 0.001%

    No Known Activations