© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9462
    Prev
    Next
    INDEX
    Explanations

    what matters

    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_40_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
     اج
    0.39
     a
    0.38
    ك
    0.38
    激情
    0.38
     дума
    0.38
     harmonies
    0.36
    messages
    0.35
     firing
    0.35
    कृष्ट
    0.35
     *"
    0.35
    POSITIVE LOGITS
     matter
    0.50
    Matter
    0.47
     Matter
    0.46
     MATTER
    0.46
     matière
    0.45
    figcaption
    0.44
     najbardziej
    0.44
    endix
    0.44
     Mosley
    0.43
    顼
    0.43
    Activations Density 0.033%

    No Known Activations