© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33169
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

    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_all/layer_41_width_262k_l0_big
    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
    हिणी
    0.43
     свидетель
    0.42
    取的
    0.37
    astos
    0.36
    mouseover
    0.35
    MouseDown
    0.35
    atmospheric
    0.35
    叨
    0.34
     mouseDown
    0.34
    𒁳
    0.34
    POSITIVE LOGITS
     gamm
    0.42
    έρα
    0.41
     doute
    0.39
     PSE
    0.39
     militaire
    0.38
    الا
    0.38
    勒
    0.38
    лії
    0.37
    Ferrari
    0.37
    HEA
    0.37
    Activations Density 0.001%

    No Known Activations