© 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. 103680
    Prev
    Next
    INDEX
    Explanations

    sanctuary cities and cathedrals

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

    tagline or, forces:, period of, Fax machines, statement of, peace and, more focus

    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
    ↵
    0.55
    Roh
    0.46
     Apparatus
    0.46
     Roh
    0.45
    us
    0.45
     wants
    0.45
    FIRST
    0.45
    FAST
    0.45
     Want
    0.43
    EAST
    0.43
    POSITIVE LOGITS
     ונ
    0.49
     stoichi
    0.47
     역할
    0.47
    恳
    0.46
     ближе
    0.45
    ٢
    0.45
     учили
    0.44
     discusión
    0.43
     profesor
    0.42
     tradición
    0.42
    Activations Density 0.000%

    No Known Activations