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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34800
    Prev
    Next
    INDEX
    Explanations

    typescript function quicksort

    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_16_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
    c
    0.70
     people
    0.58
     contemporary
    0.57
    ces
    0.55
     different
    0.55
     khác
    0.52
     ре
    0.51
     morning
    0.51
    ૩
    0.51
     по
    0.51
    POSITIVE LOGITS
    ाइम
    0.61
    positroid
    0.57
    ح
    0.56
     insectes
    0.54
    ث
    0.54
    าที
    0.53
    akana
    0.52
    ampe
    0.52
    ول
    0.52
    是在
    0.52
    Activations Density 0.000%

    No Known Activations