© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8795
    Prev
    Next
    INDEX
    Explanations

    received input or feedback

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

    originating from

    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_53_width_65k_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
     From
    0.56
     從
    0.55
     vanaf
    0.52
    From
    0.51
     davon
    0.50
     Από
    0.50
     откуда
    0.49
     从
    0.48
    ออกจาก
    0.47
     منها
    0.47
    POSITIVE LOGITS
     received
    0.67
    を受ける
    0.64
    received
    0.63
    來自
    0.60
     recieved
    0.57
     receb
    0.55
     Received
    0.52
    来自
    0.51
     RECEIVED
    0.50
    pouring
    0.49
    Activations Density 0.110%

    No Known Activations