© 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. 43026
    Prev
    Next
    INDEX
    Explanations

    container in software development

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

    html container divs

    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
    이었다
    0.52
     impressively
    0.52
     solidly
    0.49
     bên
    0.48
     superbly
    0.48
    اً
    0.48
     وګټ
    0.47
     authentically
    0.47
     appealing
    0.47
     partant
    0.47
    POSITIVE LOGITS
    ag
    0.66
    j
    0.59
    il
    0.57
    at
    0.57
    ve
    0.57
    w
    0.57
    ono
    0.56
    ec
    0.56
    ey
    0.55
    nit
    0.55
    Activations Density 0.001%

    No Known Activations