© 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. 221021
    Prev
    Next
    INDEX
    Explanations

    disconnection, cutting, division

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

    divides, decoupled, brutal, reduced

    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
    惆
    0.52
    invocation
    0.51
    عب
    0.50
    usual
    0.50
    tips
    0.50
    tweets
    0.49
    maximal
    0.48
    Ẓ
    0.48
    َّ
    0.47
    fl
    0.47
    POSITIVE LOGITS
     condensers
    0.56
     decoupled
    0.53
     cutting
    0.52
     surgically
    0.52
     aliquot
    0.52
     disconnection
    0.51
     compartmental
    0.51
     piece
    0.50
     breakage
    0.48
     cuttings
    0.48
    Activations Density 0.001%

    No Known Activations