© 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. 79144
    Prev
    Next
    INDEX
    Explanations

    infect, classic, kernels, damage, composer, orbits, sets

    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
     सोच
    0.46
     Tanjung
    0.45
     बांध
    0.44
     predictions
    0.42
     Şu
    0.42
     mengen
    0.41
    predictions
    0.41
    2
    0.41
    t
    0.41
     مشاهد
    0.40
    POSITIVE LOGITS
    বিষ্ট
    0.42
    you
    0.39
    ার্টমেন্ট
    0.38
    失去了
    0.37
    icado
    0.37
    cephalus
    0.37
     constitut
    0.37
     एडमिशन
    0.36
    valment
    0.36
    InputBorder
    0.36
    Activations Density 0.009%

    No Known Activations