© 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. 143985
    Prev
    Next
    INDEX
    Explanations

    for a number of

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

    personalized offers and understanding

    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
     us
    0.51
    V
    0.50
    vgl
    0.49
     مورد
    0.47
    が必要
    0.46
    futures
    0.46
    pwm
    0.45
    abut
    0.45
    extensions
    0.45
     subordin
    0.45
    POSITIVE LOGITS
     aventure
    0.49
    лни
    0.48
    뇰
    0.45
    办事
    0.44
     admire
    0.44
    점에서
    0.43
    𝚑
    0.43
    我家
    0.43
     avantage
    0.43
     솔
    0.43
    Activations Density 0.001%

    No Known Activations