© 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. 89585
    Prev
    Next
    INDEX
    Explanations

    intravenous administration

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

    downloading and installing plugins

    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
     cabelos
    0.51
    гой
    0.50
    骖
    0.50
    𝓷
    0.49
     да
    0.48
    няет
    0.48
    рд
    0.47
     cabel
    0.47
     canteen
    0.47
    ໌
    0.47
    POSITIVE LOGITS
     空
    0.46
     éxito
    0.46
    据
    0.44
    ething
    0.42
    重視
    0.41
    独自の
    0.41
    varnothing
    0.40
     successfully
    0.40
    成功
    0.40
     Ngo
    0.40
    Activations Density 0.000%

    No Known Activations