© 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-65K
    7. 30251
    Prev
    Next
    INDEX
    Explanations

    projects and job descriptions

    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_65k_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
    `/
    0.47
    יים
    0.45
     '/
    0.42
    おか
    0.42
     (`
    0.41
     decisions
    0.40
    א
    0.40
    /"
    0.39
    /...
    0.39
    Node
    0.39
    POSITIVE LOGITS
    ابق
    0.51
     profitable
    0.50
     hernia
    0.47
    ᱒
    0.45
    يد
    0.44
    kannt
    0.44
    profitable
    0.43
     فر
    0.43
    idcoin
    0.43
    р
    0.43
    Activations Density 0.003%

    No Known Activations