© 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. 134290
    Prev
    Next
    INDEX
    Explanations

    dry cleaning and delivery services

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

    medical rehabilitation requirements

    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
     보세요
    0.41
     ২০১৬
    0.40
     रघु
    0.40
     tracker
    0.40
     момента
    0.39
     законо
    0.39
     ✅
    0.39
     конденса
    0.39
    すぐ
    0.38
     ваших
    0.38
    POSITIVE LOGITS
     ouverture
    0.51
     nécessairement
    0.48
     déf
    0.47
     arbets
    0.47
     température
    0.45
     åp
    0.45
    ྛ
    0.45
    pero
    0.45
     évidemment
    0.44
     لوبې
    0.44
    Activations Density 0.001%

    No Known Activations