© 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. 144716
    Prev
    Next
    INDEX
    Explanations

    performance and outcome improvement

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

    previous lung disease and gorgeous lust

    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
     поговори
    0.54
    褂
    0.49
    етки
    0.48
     нагру
    0.47
    痧
    0.47
     sombra
    0.46
     выпуска
    0.46
     involuntary
    0.46
    퀵
    0.46
     училище
    0.46
    POSITIVE LOGITS
    rl
    0.51
    quality
    0.51
    yt
    0.48
    ft
    0.47
    لع
    0.46
    new
    0.45
    hl
    0.44
    lt
    0.44
     combining
    0.43
    command
    0.43
    Activations Density 0.001%

    No Known Activations