© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    lists of items, punctuation, and conjunctions

    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
     infinity
    0.36
    티
    0.35
    си
    0.35
    5
    0.34
     מא
    0.32
     the
    0.32
    R
    0.31
    T
    0.31
     rango
    0.31
    Д
    0.31
    POSITIVE LOGITS
    ℞
    0.33
    ຼ
    0.32
     thiab
    0.31
    anesulf
    0.29
    ukebox
    0.29
    loe
    0.29
     ujarnya
    0.29
     siRNA
    0.28
     Of
    0.28
     JSONObject
    0.28
    Activations Density 0.160%

    No Known Activations