© 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-16K
    7. 12950
    Prev
    Next
    INDEX
    Explanations

    specific items or destinations

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

    Customer commerce awards

    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_16k_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
     silicate
    0.47
     idiopathic
    0.45
     tetrachloride
    0.45
    rosophila
    0.44
     ribosomal
    0.43
    ^{-/-}$
    0.43
     kwenye
    0.42
     subterr
    0.42
     detergent
    0.42
    ahydro
    0.42
    POSITIVE LOGITS
     اكيد
    0.54
     Owner
    0.50
     Booking
    0.49
     अवार्ड
    0.49
     Awards
    0.49
     kunder
    0.47
     Invoice
    0.47
     Customer
    0.47
     biznes
    0.47
    💌
    0.47
    Activations Density 0.000%

    No Known Activations