© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 4399
    Prev
    Next
    INDEX
    Explanations

    react state and refs

    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
    Negative Logits
    DateTimeField
    0.47
     தமிழரசுக்
    0.47
    侘
    0.44
    槨
    0.43
    鳖
    0.43
    бора
    0.42
    Celltype
    0.42
     preoperative
    0.42
    Wild
    0.42
    𒉌
    0.42
    POSITIVE LOGITS
     state
    1.02
    useState
    0.89
    state
    0.86
     useState
    0.84
    setState
    0.82
     State
    0.80
    handleClick
    0.77
     prevState
    0.76
     handleClick
    0.76
     handleChange
    0.71
    Activations Density 0.085%

    No Known Activations