© 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. 83978
    Prev
    Next
    INDEX
    Explanations

    business concepts and actions

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

    hypothesis, within, apart, I know

    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
    Locations
    0.50
    negie
    0.47
    ۲۰
    0.46
    Ꮰ
    0.44
    Elementos
    0.44
    เพิ่มเติม
    0.44
    Location
    0.43
    𐰇
    0.43
    Animals
    0.43
    சில
    0.42
    POSITIVE LOGITS
     جميع
    0.43
     dengue
    0.43
     shayari
    0.42
    ुरा
    0.42
     Sidd
    0.41
     cæ
    0.40
    :
    0.40
     rupture
    0.40
     rupt
    0.39
     pape
    0.39
    Activations Density 0.001%

    No Known Activations