© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43662
    Prev
    Next
    INDEX
    Explanations

    financial milestones

    np_acts-logits-general · gemini-2.5-flash-lite

    approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ارو
    0.50
     alkaloids
    0.48
     annihilated
    0.46
    ADEL
    0.45
    اد
    0.45
    Ζ
    0.45
    Zb
    0.44
    Zd
    0.44
     Obsidian
    0.43
     отмечает
    0.43
    POSITIVE LOGITS
     посредством
    0.48
    ֙
    0.45
     હજાર
    0.41
    뷰
    0.40
     stimulating
    0.40
    geç
    0.40
    stimulating
    0.40
     sorprend
    0.40
     ឬ
    0.40
     Shaping
    0.39
    Activations Density 0.000%

    No Known Activations