© 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. 54004
    Prev
    Next
    INDEX
    Explanations

    want to

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

    vaping and lung health

    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
     해
    0.58
    mäßig
    0.52
     مث
    0.47
     식
    0.47
    ที่เป็น
    0.47
    estä
    0.47
     එක
    0.46
     bure
    0.46
     엘
    0.45
     कॉरिडोर
    0.45
    POSITIVE LOGITS
    ITEMS
    0.50
    ভাব
    0.50
     reviewing
    0.49
     REVIEW
    0.49
    Investigators
    0.48
     UNSIGNED
    0.47
     ITEM
    0.46
     JOHN
    0.46
     colnames
    0.46
     unpublished
    0.46
    Activations Density 0.000%

    No Known Activations