© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1075
    Prev
    Next
    INDEX
    Explanations

    building foundations and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     şark
    0.40
     dépour
    0.38
     zieht
    0.37
     vielen
    0.37
    ഏ
    0.36
    桕
    0.36
     हेव
    0.36
     remplacement
    0.35
     vilá
    0.35
    ů
    0.35
    POSITIVE LOGITS
     foundations
    0.54
     relationships
    0.50
     build
    0.46
     trust
    0.45
     foundation
    0.43
     reputation
    0.43
     credibility
    0.42
     reputations
    0.42
     Build
    0.42
     bonds
    0.41
    Activations Density 0.227%

    No Known Activations