© 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. 88723
    Prev
    Next
    INDEX
    Explanations

    auditing and financial inspection

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

    auditing official roles

    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
    >→</
    0.45
    zeb
    0.45
     όπου
    0.44
     જ્યાં
    0.44
     recher
    0.44
     அமைச்ச
    0.43
    らの
    0.43
     вър
    0.43
     אשר
    0.42
    夆
    0.42
    POSITIVE LOGITS
     Audit
    0.56
    Audit
    0.54
     auditing
    0.52
     audit
    0.50
     ایالات
    0.50
     Inspector
    0.49
     Auditors
    0.48
     Inspectors
    0.48
    ඩි
    0.47
    ’
    0.47
    Activations Density 0.000%

    No Known Activations