© 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. 235002
    Prev
    Next
    INDEX
    Explanations

    WordPress login and locations

    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
     dovol
    0.53
    蘄
    0.49
     broaden
    0.48
    ইল
    0.48
     introducir
    0.48
     virkelig
    0.48
     obič
    0.48
     njegov
    0.47
     commissioned
    0.47
     poved
    0.47
    POSITIVE LOGITS
     Manchester
    0.46
    panels
    0.45
     Brigham
    0.45
    ()<<"
    0.43
    ()
    0.42
     Panels
    0.42
     透
    0.41
     Manila
    0.41
     Manhattan
    0.41
     Fall
    0.41
    Activations Density 0.001%

    No Known Activations