© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13086
    Prev
    Next
    INDEX
    Explanations

    possession and strategic access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    钀
    0.47
    പ്പോഴും
    0.47
    㬹
    0.46
     отдела
    0.45
    Cameras
    0.45
    ାଇ
    0.43
    㫣
    0.43
    铰
    0.43
    ཆ
    0.42
     пай
    0.42
    POSITIVE LOGITS
     abundant
    0.51
     naturale
    0.47
    begin
    0.47
     naturales
    0.46
     voiced
    0.46
     strongly
    0.46
     será
    0.46
     plentiful
    0.46
     upbeat
    0.45
     early
    0.45
    Activations Density 0.003%

    No Known Activations