© 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. 208107
    Prev
    Next
    INDEX
    Explanations

    Kendall Square

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

    coax beauty, life, or creation

    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
     فرنسا
    0.54
     París
    0.49
     recto
    0.49
    AssetsResponse
    0.49
    ᕇ
    0.48
    ىن
    0.47
     సా
    0.46
    ్రె
    0.46
     متحد
    0.46
    PROCESSING
    0.45
    POSITIVE LOGITS
    0
    0.47
    name
    0.46
     प्रति
    0.44
    2
    0.44
    store
    0.43
     name
    0.43
    oustic
    0.43
    reed
    0.42
    ower
    0.41
     名称
    0.41
    Activations Density 0.000%

    No Known Activations