© 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. 90637
    Prev
    Next
    INDEX
    Explanations

    models following technology

    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
    ت
    0.54
    т
    0.50
    ת
    0.47
    legenheit
    0.47
    إن
    0.46
    tional
    0.46
    tion
    0.45
    ૬
    0.44
     welke
    0.43
     искусства
    0.43
    POSITIVE LOGITS
     treks
    0.51
     centuries
    0.50
     kilograms
    0.50
     backpacks
    0.50
     sclerosis
    0.48
     esi
    0.48
     optomet
    0.48
     qilish
    0.47
     blisters
    0.47
     trekking
    0.46
    Activations Density 0.002%

    No Known Activations