© 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. 70754
    Prev
    Next
    INDEX
    Explanations

    we will, suddenly he, links with

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

    incentives, Turkey, orbit, distance

    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
     будущего
    0.53
     Propulsion
    0.47
     基于
    0.46
    뇰
    0.44
    曌
    0.44
    фикации
    0.44
    艨
    0.44
    т
    0.43
    법
    0.43
     왔다
    0.43
    POSITIVE LOGITS
     potrav
    0.49
    でしたが
    0.47
     cher
    0.47
     wooded
    0.46
     heeft
    0.45
     pobreza
    0.44
     drags
    0.44
    していますが
    0.44
    }\
    0.44
     pasture
    0.44
    Activations Density 0.001%

    No Known Activations