© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9227
    Prev
    Next
    INDEX
    Explanations

    ownership stakes and shares

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

    company equity and ownership

    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_40_width_16k_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
    überküloz
    0.44
    bezpie
    0.42
    歼
    0.41
     уро
    0.39
     жан
    0.39
    附件
    0.39
    ikalische
    0.39
    สัตว์
    0.39
    络
    0.39
    בול
    0.39
    POSITIVE LOGITS
     shareholders
    2.03
     shareholder
    2.03
     Shareholders
    1.88
    股东
    1.76
     stockholders
    1.71
     stockholder
    1.70
     shares
    1.58
     Shares
    1.45
     equity
    1.43
    股
    1.41
    Activations Density 0.276%

    No Known Activations