© 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. 245556
    Prev
    Next
    INDEX
    Explanations

    discharge disposition agreement payment

    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
     услы
    0.53
    邕
    0.52
     результа
    0.50
     вопро
    0.49
    ৩২
    0.49
    ချ
    0.47
    ቮ
    0.47
    си
    0.47
    采购
    0.45
     розу
    0.45
    POSITIVE LOGITS
    ,
    0.56
     =
    0.47
     autosomal
    0.46
     pembayaran
    0.46
     gris
    0.44
     payment
    0.44
     terrestrial
    0.44
     private
    0.44
     ("
    0.44
     (
    0.43
    Activations Density 0.000%

    No Known Activations