© 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. 216112
    Prev
    Next
    INDEX
    Explanations

    geographical directions and specific terms

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

    location and status indicators

    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
    магази
    0.52
    single
    0.51
     देखो
    0.51
     Акысыз
    0.50
    deny
    0.50
    krét
    0.50
    produkte
    0.50
     responsables
    0.49
    𝚈
    0.48
    plica
    0.48
    POSITIVE LOGITS
     Sur
    0.51
     East
    0.47
    0.47
     애플
    0.46
     Barriers
    0.44
     Inland
    0.43
     Queries
    0.43
     Hudson
    0.42
     Eastern
    0.41
     Rings
    0.41
    Activations Density 0.000%

    No Known Activations