© 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. 144844
    Prev
    Next
    INDEX
    Explanations

    look like the

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

    code, blog, soil

    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
    íguez
    0.45
    cohols
    0.44
    you
    0.42
    fishing
    0.42
     agricultura
    0.41
     برج
    0.41
    boks
    0.40
    δ
    0.40
     समझा
    0.40
    ত্ব
    0.40
    POSITIVE LOGITS
     painstaking
    0.46
     manic
    0.46
    ﭔ
    0.44
     таблицы
    0.42
     vem
    0.42
     veritable
    0.42
     Mojave
    0.42
     ozone
    0.41
     journeys
    0.40
     microarray
    0.40
    Activations Density 0.001%

    No Known Activations