© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189539
    Prev
    Next
    INDEX
    Explanations

    skin, great, list, treating

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

    explaining capability or emotion

    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
     Caucus
    0.51
     viime
    0.48
    ക
    0.48
     Sikhs
    0.47
     प्रतिबि
    0.47
     tempHeader
    0.46
    isPreview
    0.46
     रूपा
    0.45
     コットン
    0.45
    नं
    0.45
    POSITIVE LOGITS
    沸
    0.48
    stellen
    0.46
    tone
    0.46
    пен
    0.44
    สงค์
    0.42
    plet
    0.42
    раи
    0.42
    march
    0.42
    tien
    0.42
    rik
    0.41
    Activations Density 0.000%

    No Known Activations