© 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. 190809
    Prev
    Next
    INDEX
    Explanations

    differential twisted pair / serial

    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
    मर्श
    0.44
    ᱘
    0.41
     lộ
    0.38
    thickmathspace
    0.38
     [['
    0.37
     [{
    0.37
    Jika
    0.37
     хотят
    0.36
    ChoiceItemLayout
    0.36
    淈
    0.36
    POSITIVE LOGITS
     cousin
    0.38
     feathers
    0.38
     Cousin
    0.38
     offers
    0.37
     regulates
    0.37
     wildflower
    0.37
     wildflowers
    0.37
     homology
    0.37
     létre
    0.37
    lookandfeel
    0.36
    Activations Density 0.000%

    No Known Activations