© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8822
    Prev
    Next
    INDEX
    Explanations

    status classification affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    要望
    0.85
     esforços
    0.81
     esercizi
    0.80
     glLight
    0.80
     forecasting
    0.79
     paced
    0.79
     ejercicios
    0.78
    LEncoder
    0.77
    㕵
    0.77
     MessageBox
    0.77
    POSITIVE LOGITS
     status
    2.05
    status
    1.90
     statuses
    1.76
     Status
    1.75
    Status
    1.74
     classification
    1.68
    身份
    1.64
     статус
    1.58
     classifications
    1.58
     affiliation
    1.56
    Activations Density 0.356%

    No Known Activations