© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106519
    Prev
    Next
    INDEX
    Explanations

    surface, US, ceramic, State, Greek

    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_16_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
    ri
    0.52
     vanity
    0.50
    目
    0.49
    几
    0.48
    нией
    0.46
    ുകൾ
    0.46
     miner
    0.46
    록
    0.46
    押
    0.45
     ува
    0.45
    POSITIVE LOGITS
    AbsolutePath
    0.54
    ☹
    0.53
    Theory
    0.52
    Amy
    0.51
    fda
    0.51
    ভাগ্য
    0.49
    】.
    0.49
    Kin
    0.49
    Histogram
    0.48
    Blogs
    0.48
    Activations Density 0.000%

    No Known Activations