© 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-16K
    7. 6958
    Prev
    Next
    INDEX
    Explanations

    language processing

    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_16k_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
    www
    0.38
    мпаваць
    0.37
    ём
    0.36
    न्दावन
    0.36
    اضره
    0.34
    液
    0.34
    שים
    0.34
    加速度
    0.33
    شي
    0.33
    其它
    0.33
    POSITIVE LOGITS
     A
    0.45
    ara
    0.41
     অনুবাদ
    0.40
     ബ
    0.37
    （
    0.37
    ezza
    0.36
    bedkar
    0.36
    am
    0.36
     Airbnb
    0.35
     translations
    0.35
    Activations Density 0.303%

    No Known Activations