© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7475
    Prev
    Next
    INDEX
    Explanations

    common function words and categories

    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
    Deployment
    0.47
    Hed
    0.47
     معد
    0.46
    Department
    0.46
    bri
    0.46
    瓤
    0.46
    father
    0.45
    am
    0.44
    Examples
    0.44
    Henry
    0.44
    POSITIVE LOGITS
     ~\
    0.47
     дол
    0.46
     (-\
    0.46
    టన
    0.45
    gica
    0.45
    గ
    0.45
    。",
    0.44
    ագր
    0.44
     og
    0.43
     speculate
    0.43
    Activations Density 0.001%

    No Known Activations