© 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. 22885
    Prev
    Next
    INDEX
    Explanations

    differences between concepts

    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
     পাবে
    0.46
     исте
    0.44
    го
    0.42
    ນາ
    0.42
    f
    0.41
    KM
    0.41
    為主
    0.41
    只能
    0.40
     હશે
    0.40
    ULD
    0.39
    POSITIVE LOGITS
     phẩm
    0.42
     interrelated
    0.41
     polynom
    0.41
     mathemat
    0.41
     zowel
    0.40
     clazz
    0.40
     proport
    0.39
     femoral
    0.39
     Maverick
    0.39
     রোববার
    0.39
    Activations Density 0.017%

    No Known Activations