© 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. 206712
    Prev
    Next
    INDEX
    Explanations

    will be

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

    While followed by a contrast

    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
    يش
    0.51
    pertoire
    0.50
    ضا
    0.49
    وار
    0.47
    لت
    0.46
    ك
    0.46
    lectricité
    0.44
    صر
    0.43
    ضة
    0.43
     Fasc
    0.43
    POSITIVE LOGITS
     digunakan
    0.61
    ௦
    0.56
     kertas
    0.54
    druck
    0.52
    োডে
    0.49
     USED
    0.49
     исследова
    0.48
     Oogie
    0.48
    荩
    0.48
     काग
    0.48
    Activations Density 0.001%

    No Known Activations