© 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. 242959
    Prev
    Next
    INDEX
    Explanations

    transaction and foreign languages

    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
    線
    0.49
    boek
    0.47
     تمام
    0.47
     following
    0.46
     pastures
    0.43
    欖
    0.42
    रल
    0.42
    线
    0.42
    watering
    0.41
    我們
    0.41
    POSITIVE LOGITS
     TRANSACTION
    0.48
     dirinya
    0.45
    ธุรก
    0.45
     FabD
    0.43
     UNNEEDED
    0.43
     Chines
    0.43
     девушка
    0.42
    ла
    0.42
     GRAPH
    0.42
     तुमचे
    0.42
    Activations Density 0.000%

    No Known Activations