© 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. 28373
    Prev
    Next
    INDEX
    Explanations

    joint property division

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

    joint financial assets

    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
     реб
    0.43
     অভাব
    0.41
     Explos
    0.39
     retrou
    0.39
    ()):
    0.39
    పర్
    0.38
     Brend
    0.38
     déchir
    0.38
    开车
    0.37
    嘢
    0.37
    POSITIVE LOGITS
     joint
    0.45
     wspól
    0.45
    Joint
    0.42
    Shared
    0.41
     proporcional
    0.41
     jointly
    0.41
     binary
    0.41
     booties
    0.41
     пропор
    0.41
     shared
    0.40
    Activations Density 0.045%

    No Known Activations