© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1728
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    ாதார
    0.32
    า
    0.32
    ()}
    0.30
    ân
    0.30
    nętr
    0.30
    gunakan
    0.28
    produk
    0.28
    ͈
    0.28
    ública
    0.28
     технических
    0.27
    POSITIVE LOGITS
     THAT
    0.39
     twor
    0.33
     that
    0.31
     Changes
    0.31
     Dance
    0.30
     iki
    0.30
     Pick
    0.29
     Lost
    0.29
     duas
    0.29
     viel
    0.29
    Activations Density 2.114%

    No Known Activations