© 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. 34114
    Prev
    Next
    INDEX
    Explanations

    legal jurisdiction or contractual clauses

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

    decimal numbers, floating-point, federal contractors

    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
    确保
    0.47
    ？
    0.43
     ？
    0.41
     થશે
    0.41
     olacaktır
    0.41
     되겠
    0.40
     will
    0.39
     της
    0.39
    ：%
    0.39
     ক্ষে
    0.38
    POSITIVE LOGITS
     obligé
    0.51
     huddled
    0.45
     limitado
    0.44
     militari
    0.44
     meus
    0.42
     segit
    0.42
     escola
    0.41
     پژوه
    0.41
    کت
    0.41
     quadrados
    0.41
    Activations Density 0.000%

    No Known Activations