© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47377
    Prev
    Next
    INDEX
    Explanations

    common contrasting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    0.41
    淮
    0.41
    onavir
    0.41
     honors
    0.40
    veranst
    0.39
    案
    0.39
    ionario
    0.39
    ૃ
    0.38
    roasted
    0.38
     выру
    0.38
    POSITIVE LOGITS
     सभ्यता
    0.54
     پلی
    0.47
    스는
    0.46
     erau
    0.46
     dent
    0.45
    Ges
    0.43
    传感器
    0.43
     سوریه
    0.42
     खिलाफ
    0.42
     ব্যপারে
    0.42
    Activations Density 0.000%

    No Known Activations