© 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. 4506
    Prev
    Next
    INDEX
    Explanations

    according to you

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

    retailer and manufacturer emails

    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
    之前
    0.48
    ाने
    0.48
     palud
    0.46
    此次
    0.43
    キシ
    0.42
    నిక
    0.42
    (−
    0.42
    枚举
    0.42
    熟悉
    0.42
    ناد
    0.41
    POSITIVE LOGITS
    according
    0.49
     deux
    0.48
    your
    0.48
    ܀
    0.48
     دو
    0.47
     according
    0.46
    deux
    0.46
     دولار
    0.46
     Hương
    0.45
     কো
    0.44
    Activations Density 0.000%

    No Known Activations