© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66293
    Prev
    Next
    INDEX
    Explanations

    javascript ui components

    np_acts-logits-general · gemini-2.5-flash-lite

    code modules and utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currentPage
    0.45
    used
    0.44
    emps
    0.41
    った
    0.40
    primary
    0.40
    urname
    0.40
    ='"+
    0.40
    :",
    0.40
    ):
    0.39
    jobNumber
    0.39
    POSITIVE LOGITS
     utils
    0.61
     Utils
    0.46
     contexts
    0.45
    utils
    0.45
     hét
    0.45
     Beiträge
    0.45
     UTIL
    0.44
     utiliz
    0.43
     बँ
    0.43
    の種類
    0.42
    Activations Density 0.002%

    No Known Activations