© 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. 152827
    Prev
    Next
    INDEX
    Explanations

    culture, copyright, understanding

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

    boundaries and access control

    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
     determine
    0.53
     are
    0.51
     initialize
    0.50
     boolean
    0.50
     ruins
    0.50
     rooted
    0.48
     consequ
    0.47
    /**
    0.46
     acabado
    0.46
     do
    0.46
    POSITIVE LOGITS
    ut
    0.51
     kapas
    0.51
    ad
    0.49
    기
    0.49
    at
    0.49
    રા
    0.49
    it
    0.49
    per
    0.48
    me
    0.48
    itul
    0.48
    Activations Density 0.000%

    No Known Activations