© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    explaining "this is"

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

    this is because

    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
     stupidity
    0.56
    aný
    0.54
     IMPORTANT
    0.50
     patří
    0.50
     문제입니다
    0.50
    ")->
    0.50
     മറ്റൊരു
    0.49
    𝕖
    0.49
     untrue
    0.49
    𝚐
    0.48
    POSITIVE LOGITS
    0.54
    尤其
    0.49
     особенно
    0.47
    考虑到
    0.45
    所谓的
    0.42
    认为
    0.41
    ussi
    0.41
    特に
    0.40
    Сто
    0.40
     showcased
    0.40
    Activations Density 0.057%

    No Known Activations