© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4486
    Prev
    Next
    INDEX
    Explanations

    cancelling an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Accom
    1.00
    仓
    1.00
     Histor
    0.98
    yum
    0.97
     Illustrations
    0.96
     Protok
    0.95
     Along
    0.94
    ……………………
    0.94
     Redist
    0.93
     Zal
    0.92
    POSITIVE LOGITS
     a
    2.75
     sebuah
    2.61
     seseorang
    2.61
    特定の
    2.33
     suatu
    2.31
     isang
    2.18
     seorang
    2.17
    一台
    2.15
    一個人
    2.11
     someone
    2.08
    Activations Density 0.545%

    No Known Activations