© 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-65K
    7. 1333
    Prev
    Next
    INDEX
    Explanations

    setting up models

    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_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
     cic
    0.28
     leon
    0.27
    ન્ડ
    0.27
     Britannica
    0.27
    뿅
    0.27
    ających
    0.27
     Stanis
    0.26
     پڑھی
    0.26
     Polymer
    0.26
     hereunder
    0.26
    POSITIVE LOGITS
     категори
    0.32
    ##
    0.29
     Bali
    0.28
    Bali
    0.27
     malheureusement
    0.27
    CASCADE
    0.26
    这话
    0.25
     implications
    0.24
     quantifiable
    0.23
    дини
    0.23
    Activations Density 0.189%

    No Known Activations