© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22916
    Prev
    Next
    INDEX
    Explanations

    gain, elevation, weight, recruitment

    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_all/layer_41_width_262k_l0_big
    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
     mattis
    0.43
    gz
    0.42
     درآمد
    0.41
    锞
    0.40
    ッドレス
    0.39
     Saving
    0.39
     Drag
    0.39
    Arquivo
    0.39
    cur
    0.38
     savers
    0.38
    POSITIVE LOGITS
     набира
    1.34
     набор
    1.05
     gaining
    0.93
     gain
    0.91
     recruitment
    0.89
    招
    0.84
     recruiting
    0.80
     gained
    0.78
     recruit
    0.76
     Recruitment
    0.76
    Activations Density 0.001%

    No Known Activations