© 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. 128758
    Prev
    Next
    INDEX
    Explanations

    ending or completing actions

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

    lesion segmentation

    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
     தொடர்பு
    0.49
    ul
    0.47
     அதிசய
    0.46
    規格
    0.46
     الأص
    0.46
     الأخ
    0.46
     ث
    0.45
     設定
    0.44
     المستقبل
    0.44
     الكم
    0.43
    POSITIVE LOGITS
    переди
    0.54
     spinors
    0.51
     polluting
    0.48
     SISO
    0.47
     augmentation
    0.47
     cases
    0.46
     instances
    0.46
    하
    0.46
    Lorsque
    0.45
     mannit
    0.45
    Activations Density 0.000%

    No Known Activations