© 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. 154503
    Prev
    Next
    INDEX
    Explanations

    need to, if you, purchasing a, renting a

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

    curse gap petite especially design

    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
    T
    0.46
    OptionPane
    0.42
    Beef
    0.41
     presidential
    0.40
     settings
    0.39
     strana
    0.39
    Pong
    0.39
     bond
    0.39
    >(
    0.39
     buget
    0.38
    POSITIVE LOGITS
     ایرانی
    0.60
    festival
    0.57
    殮
    0.51
    赶紧
    0.50
     मेट्रो
    0.49
     русских
    0.49
     aujourd
    0.49
    ific
    0.48
    ༡
    0.48
     trabaja
    0.48
    Activations Density 0.004%

    No Known Activations