© 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. 69528
    Prev
    Next
    INDEX
    Explanations

    action, equations, holiday, state

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

    components with conjunctions

    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
     as
    0.51
     তৈরির
    0.50
    ola
    0.49
    ,
    0.48
     आना
    0.48
    itis
    0.48
     ग
    0.47
    ayan
    0.47
     and
    0.46
    ling
    0.46
    POSITIVE LOGITS
    큰
    0.54
     conservar
    0.48
    鐩
    0.48
    蛞
    0.47
    եկ
    0.46
    较大
    0.46
     conservación
    0.46
     fé
    0.45
    руют
    0.45
    Conserv
    0.45
    Activations Density 0.000%

    No Known Activations