© 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. 48105
    Prev
    Next
    INDEX
    Explanations

    errors or follow

    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
     createFile
    0.47
     ۲۰۱
    0.42
     ரா
    0.40
    getAll
    0.40
    URIS
    0.40
    uraea
    0.40
    頩
    0.40
    యాన్ని
    0.39
     २०१
    0.39
    UITableView
    0.39
    POSITIVE LOGITS
     doses
    0.46
     herbicides
    0.44
     formulas
    0.43
     coefficients
    0.43
     slides
    0.43
     shades
    0.43
     sponsors
    0.42
    t
    0.42
    ゴールド
    0.42
     sciences
    0.42
    Activations Density 0.001%

    No Known Activations