© 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. 233258
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     materialistic
    0.57
    being
    0.56
    /
    0.56
     being
    0.54
     തന്നെ
    0.51
    等が
    0.49
    ѕ
    0.48
     jakie
    0.48
     gerne
    0.48
    wellery
    0.48
    POSITIVE LOGITS
     তবু
    0.59
    媲
    0.58
     쓰는
    0.52
     đánh
    0.50
    仿佛
    0.50
     quizá
    0.49
    内核
    0.49
     పథ
    0.48
     üç
    0.47
     yalnızca
    0.47
    Activations Density 0.027%

    No Known Activations