© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56861
    Prev
    Next
    INDEX
    Explanations

    sensing or spreading

    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_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
    down
    0.49
    t
    0.48
    it
    0.46
    in
    0.43
    age
    0.41
    见了
    0.39
    翻
    0.39
    迂
    0.39
    time
    0.39
    hyper
    0.38
    POSITIVE LOGITS
     DHL
    0.50
     Lobkowicz
    0.49
     Álvaro
    0.49
     catamaran
    0.47
     lensing
    0.46
     Loire
    0.46
     ἢ
    0.45
     foie
    0.45
     Airbus
    0.44
     paypal
    0.44
    Activations Density 0.001%

    No Known Activations