© 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. 52222
    Prev
    Next
    INDEX
    Explanations

    concentration, peace of mind

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

    crecimiento, investment, volume, online

    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
     and
    0.52
     only
    0.50
     tablets
    0.50
     regions
    0.48
     \&
    0.47
     predicates
    0.45
     mats
    0.44
     condensers
    0.44
     TestCase
    0.44
     brack
    0.44
    POSITIVE LOGITS
    施工
    0.59
    加班
    0.59
    創意
    0.52
    盯着
    0.52
     கட்டுமானம்
    0.52
    資金
    0.51
     crescimento
    0.50
     проекту
    0.49
    動き
    0.49
    壽
    0.49
    Activations Density 0.001%

    No Known Activations