© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3996
    Prev
    Next
    INDEX
    Explanations

    standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    illust
    1.97
     rebirth
    1.58
     }.
    1.55
     vlog
    1.54
    illustration
    1.54
    illustrations
    1.52
    journal
    1.50
     $\}$
    1.50
     towel
    1.49
    focused
    1.48
    POSITIVE LOGITS
    غات
    1.78
     konc
    1.66
    berra
    1.63
    दर्शिता
    1.61
     comedor
    1.58
    বারের
    1.58
    পালা
    1.57
    ibilidades
    1.57
    崧
    1.55
     fabricantes
    1.54
    Activations Density 0.042%

    No Known Activations