© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49008
    Prev
    Next
    INDEX
    Explanations

    event binding and UI structure

    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_40_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
     Yorker
    0.39
     tanger
    0.39
     Colton
    0.38
     pusher
    0.37
    unlock
    0.36
     разработан
    0.36
    甑
    0.36
    εσ
    0.36
     pantalones
    0.36
     मिथुन
    0.35
    POSITIVE LOGITS
     subordinate
    0.41
    rechts
    0.38
     subordinates
    0.38
     elements
    0.37
    ']>;
    0.37
    昛
    0.37
     सहाय
    0.36
     Events
    0.36
     Binding
    0.36
     proprietà
    0.36
    Activations Density 0.003%

    No Known Activations