© 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. 91109
    Prev
    Next
    INDEX
    Explanations

    ReLU, squares, display, data, Europe

    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
    vet
    0.47
    sj
    0.46
     шли
    0.45
    sh
    0.45
     banane
    0.44
    uva
    0.44
     визуа
    0.44
    v
    0.43
     alluvial
    0.43
    rk
    0.42
    POSITIVE LOGITS
    Services
    0.49
    兜
    0.46
    Directory
    0.45
    Substring
    0.45
     Ty
    0.44
    Package
    0.42
    Pkg
    0.42
    Solutions
    0.41
     Tyre
    0.41
    Messages
    0.41
    Activations Density 0.002%

    No Known Activations