© 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. 22138
    Prev
    Next
    INDEX
    Explanations

    Derby trends, Market, invoices, string

    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
     ক্ষত্র
    0.46
    筅
    0.44
     ビタミン
    0.44
    Measurement
    0.43
    鍘
    0.43
     раствор
    0.43
    ξεις
    0.41
    铯
    0.41
    NaOMe
    0.41
     نظم
    0.40
    POSITIVE LOGITS
     come
    0.40
    do
    0.39
     China
    0.39
    ac
    0.38
    ");
    0.37
     accusing
    0.37
    im
    0.37
     read
    0.37
     auto
    0.37
     Trying
    0.37
    Activations Density 0.000%

    No Known Activations