© 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. 129029
    Prev
    Next
    INDEX
    Explanations

    introducing something or someone

    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
    اندان
    0.51
     mudar
    0.48
     marching
    0.47
    疗
    0.45
    лі
    0.44
     misconduct
    0.44
     Theodore
    0.44
     efectivo
    0.44
     lying
    0.44
    λή
    0.44
    POSITIVE LOGITS
    0
    0.54
    Node
    0.49
    ত
    0.48
    istra
    0.47
    3
    0.46
    yj
    0.45
    은
    0.44
    О
    0.43
    adapters
    0.43
    Na
    0.42
    Activations Density 0.005%

    No Known Activations