© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3771
    Prev
    Next
    INDEX
    Explanations

    You can find information

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Lord
    0.69
     Signaling
    0.67
     Nucleaire
    0.66
    ServerSocket
    0.65
    ம்பர்
    0.65
    
    0.64
     congressman
    0.63
     dynast
    0.63
    주
    0.63
     nuclé
    0.62
    POSITIVE LOGITS
     agenda
    1.14
    agenda
    1.08
     Agenda
    0.99
     agendas
    0.94
     budgeted
    0.88
    Agenda
    0.87
    motion
    0.85
     motion
    0.85
     regular
    0.85
     budget
    0.82
    Activations Density 0.108%

    No Known Activations