© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 666
    Prev
    Next
    INDEX
    Explanations

    named entities and locations

    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_40_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
     بیاکت
    0.30
     Verhalten
    0.30
     rezat
    0.29
    <unused2017>
    0.29
    kannt
    0.28
     값을
    0.28
     belladone
    0.28
     Riemannian
    0.28
    ektedir
    0.28
    <unused1838>
    0.28
    POSITIVE LOGITS
     Park
    0.37
     Museum
    0.37
     Memorial
    0.34
     Golf
    0.32
     Gardens
    0.32
     Heights
    0.32
     Square
    0.31
     parks
    0.31
     Village
    0.31
     museum
    0.31
    Activations Density 0.027%

    No Known Activations