© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    code comments and object declarations

    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
    aland
    1.26
    ending
    1.18
     vase
    1.09
    ande
    1.01
     therefore
    1.00
    </h2>
    1.00
    </h4>
    1.00
     meanwhile
    0.99
    eland
    0.97
     Vase
    0.97
    POSITIVE LOGITS
     "+
    1.14
    جهة
    1.08
    某些
    1.07
    وروب
    1.05
    靄
    1.04
     "**
    1.04
     “[
    1.04
    ترة
    1.02
    รอง
    1.02
    جهات
    1.02
    Activations Density 0.151%

    No Known Activations