© 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. 158524
    Prev
    Next
    INDEX
    Explanations

    future actions and outcomes

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

    dispenser, own, flow, strong, evolving

    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
    ordu
    0.47
     सकते
    0.47
     এসেছিলেন
    0.47
     electrónicos
    0.45
     indemn
    0.43
     ტ
    0.43
    ERVER
    0.43
     הק
    0.42
     usados
    0.41
     portes
    0.41
    POSITIVE LOGITS
    ため
    0.50
    誕生
    0.49
    元
    0.49
    ва
    0.48
    ки
    0.47
    ഷ്യ
    0.47
    いろいろ
    0.47
     evolving
    0.46
    わり
    0.46
    文章
    0.46
    Activations Density 0.000%

    No Known Activations