© 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. 9643
    Prev
    Next
    INDEX
    Explanations

    science and technical terms

    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
     ½
    0.47
     hundred
    0.44
    th
    0.41
    T
    0.41
    ½
    0.40
    W
    0.40
    日
    0.40
    D
    0.39
    1
    0.38
    5
    0.38
    POSITIVE LOGITS
    phosphine
    0.38
    iscale
    0.35
     Metadata
    0.34
     bactéries
    0.34
     জিন
    0.32
    Coords
    0.32
     substrings
    0.32
    ocortic
    0.32
     Semantic
    0.32
    ronaut
    0.31
    Activations Density 0.107%

    No Known Activations