© 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. 48748
    Prev
    Next
    INDEX
    Explanations

    often worry, disinfecting wipes

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

    disinfectant, fever, deficiency, dizziness

    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
    <strong>
    0.52
    m
    0.51
    <code>
    0.50
    4
    0.49
    以
    0.48
    k
    0.47
    j
    0.47
     以
    0.47
     Cornish
    0.46
    <sub>
    0.46
    POSITIVE LOGITS
    뿯
    0.51
     ойной
    0.48
    ீன்
    0.48
    pyrazine
    0.47
     अधिकार
    0.47
    ພວກເຮ
    0.46
    ন্তন
    0.46
    ╅
    0.46
    เปอร์
    0.46
    yata
    0.46
    Activations Density 0.001%

    No Known Activations