© 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. 89409
    Prev
    Next
    INDEX
    Explanations

    general topics or common processes

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

    rules, policies, requirements, conditions

    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
     r
    0.55
     cl
    0.52
     by
    0.49
     ity
    0.48
     n
    0.48
     new
    0.48
    n
    0.47
    ings
    0.47
     future
    0.47
    ity
    0.47
    POSITIVE LOGITS
    美国的
    0.60
    一般的な
    0.59
     ایالات
    0.56
    चीनी
    0.54
     ক্রয়
    0.52
     பொருட்களை
    0.52
    一般的
    0.51
    瞍
    0.51
     неболь
    0.50
    照顾
    0.50
    Activations Density 0.000%

    No Known Activations