© 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. 134373
    Prev
    Next
    INDEX
    Explanations

    financial and logistical terms

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

    script and model development

    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
    ج
    0.59
     Chag
    0.53
     aswell
    0.52
     صف
    0.51
    ية
    0.50
    𝐧
    0.49
     ឬ
    0.49
     darf
    0.48
     whole
    0.48
     وليس
    0.48
    POSITIVE LOGITS
     radii
    0.43
     ennemis
    0.43
     milhões
    0.42
     iodide
    0.41
    kę
    0.41
    ​]]
    0.40
     большим
    0.39
    ioribus
    0.39
     bosons
    0.39
     базы
    0.39
    Activations Density 0.001%

    No Known Activations