© 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. 22062
    Prev
    Next
    INDEX
    Explanations

    authority to execute or sign

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

    authorized to act or bind

    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
    所谓的
    0.46
    照顧
    0.45
    怙
    0.44
    所谓
    0.43
    黾
    0.43
    calcular
    0.42
     miljø
    0.42
     স্নেহ
    0.42
     эко
    0.41
     सम्बन्ध
    0.40
    POSITIVE LOGITS
     директор
    0.42
     authorized
    0.42
     Curt
    0.42
     authorize
    0.40
    atories
    0.39
    యా
    0.39
    </td>
    0.38
     kuri
    0.38
     comunicado
    0.38
     выпуска
    0.38
    Activations Density 0.006%

    No Known Activations