© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6830
    Prev
    Next
    INDEX
    Explanations

    experience level options

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     festival
    0.96
    سال
    0.95
     recruits
    0.92
     comprim
    0.92
     Festival
    0.91
    诓
    0.91
     festivals
    0.90
    虚拟机
    0.90
    쳥
    0.89
     Festivals
    0.89
    POSITIVE LOGITS
     ownership
    4.14
     owner
    3.95
     owners
    3.93
     Ownership
    3.87
    owner
    3.81
     Owner
    3.75
    ownership
    3.73
     Owners
    3.68
    owners
    3.67
    Owners
    3.62
    Activations Density 0.401%

    No Known Activations