© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143362
    Prev
    Next
    INDEX
    Explanations

    American examples or imagery

    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
    Not in Any Lists

    No Comments

    Negative Logits
    was
    0.52
    CI
    0.48
    ciju
    0.44
    vero
    0.44
    remark
    0.43
    -
    0.43
    C
    0.41
    ba
    0.41
    atu
    0.41
    case
    0.41
    POSITIVE LOGITS
     coercive
    0.54
     tyrannical
    0.53
     docile
    0.52
     pacif
    0.51
     mods
    0.51
     atualmente
    0.51
     solitons
    0.50
     futur
    0.48
     rival
    0.48
     sopa
    0.48
    Activations Density 0.006%

    No Known Activations