© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180039
    Prev
    Next
    INDEX
    Explanations

    invent or disclose processes

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

    location specificity

    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
    Negative Logits
    箓
    0.52
    ższ
    0.51
     トレー
    0.49
    有机
    0.49
    żenia
    0.49
     ምግብ
    0.49
     энерги
    0.49
     журнала
    0.47
    젤
    0.46
    CCCO
    0.46
    POSITIVE LOGITS
     whanne
    0.52
     having
    0.50
     lieutenant
    0.46
     respectively
    0.45
     Leuven
    0.45
     relating
    0.45
     داشته
    0.44
     witnessing
    0.44
     lathes
    0.43
     together
    0.42
    Activations Density 0.001%

    No Known Activations