© 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. 30653
    Prev
    Next
    INDEX
    Explanations

    any applicable law or such terms

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

    list, number at the beginning/end of the list.duplicates/weak points and selecting the top 5 featuresstatement that *must* be trueMinimized antibiotic exposure. * Limitations: * Not for PyelonephritisRequires more setup and/or specific equipmentRecovered well after a less-than-stellar startday to night gives them the edgeskirt, specifically a pleated, micro, and miniskirtStyles I can *adopt* based on your prompting

    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
     kter
    0.45
    {\'
    0.43
    まとめ
    0.42
    အတွက်
    0.41
    摶
    0.41
     অজ্ঞ
    0.40
    \"{
    0.40
     ಹೀ
    0.39
    _{{\
    0.39
    まとめて
    0.39
    POSITIVE LOGITS
    uki
    0.41
    هما
    0.40
     Jesus
    0.38
    鸦
    0.38
    ‍या
    0.37
     Idaho
    0.37
    したり
    0.36
    irrah
    0.36
     ledge
    0.35
     Nature
    0.35
    Activations Density 0.002%

    No Known Activations