© 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. 21870
    Prev
    Next
    INDEX
    Explanations

    numerical sequences with operators

    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
     transportar
    0.38
     Buena
    0.37
     poderão
    0.36
    庖
    0.36
     Horst
    0.36
     recentemente
    0.36
    ومان
    0.35
    *}{
    0.35
     möchte
    0.35
     oferecer
    0.35
    POSITIVE LOGITS
    joint
    0.39
     grind
    0.39
    ق
    0.39
     decays
    0.38
     API
    0.38
    rel
    0.38
    vstack
    0.37
    ray
    0.37
    .”)
    0.37
     termin
    0.36
    Activations Density 0.001%

    No Known Activations