© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79684
    Prev
    Next
    INDEX
    Explanations

    popular in

    np_acts-logits-general · gemini-2.5-flash-lite

    boredom is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sloan
    0.46
     deseas
    0.46
     ligament
    0.45
     choral
    0.45
     I
    0.44
     lime
    0.43
     cang
    0.43
     loy
    0.43
     sejam
    0.43
    iénd
    0.42
    POSITIVE LOGITS
    स्पति
    0.44
    閘
    0.43
    ρηση
    0.42
    UART
    0.42
    USART
    0.42
     غادي
    0.42
     কিছুক্ষণ
    0.42
    呵呵
    0.41
    DefineConstants
    0.41
    Mockito
    0.41
    Activations Density 0.000%

    No Known Activations