© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7033
    Prev
    Next
    INDEX
    Explanations

    old concepts become replaced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     analytics
    0.94
     multimedia
    0.89
     Analytics
    0.87
     Intelligence
    0.80
    维度
    0.78
     Metrics
    0.78
     vooraf
    0.78
     Pizza
    0.78
    analytics
    0.77
    蚂
    0.77
    POSITIVE LOGITS
     reappear
    0.91
     sporadically
    0.88
     disappeared
    0.85
     replaced
    0.84
    Replacement
    0.83
     reapp
    0.83
     remnant
    0.83
     now
    0.81
     desaparecer
    0.80
    replaced
    0.80
    Activations Density 0.534%

    No Known Activations