© 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. 222663
    Prev
    Next
    INDEX
    Explanations

    married (MRIN:...)

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

    specific instruction keywords

    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
     DOE
    0.52
     Humanities
    0.50
     哈
    0.49
     önemlidir
    0.49
     doprav
    0.49
     önemli
    0.48
     平
    0.48
     Tompkins
    0.48
     Certificates
    0.48
     Apar
    0.47
    POSITIVE LOGITS
    その後
    0.55
    convex
    0.54
    顰
    0.48
    刺繍
    0.46
    tracing
    0.45
    すぐ
    0.45
    しばらく
    0.45
    そうだ
    0.45
    fallback
    0.44
    빴
    0.44
    Activations Density 0.000%

    No Known Activations