© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12680
    Prev
    Next
    INDEX
    Explanations

    education

    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_13_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
    Мушко
    2.15
     appreciate
    2.07
    appro
    2.05
    記得
    2.04
    Compilation
    2.01
     ";
    2.01
    います
    1.99
    published
    1.97
     博文
    1.96
    ராத
    1.95
    POSITIVE LOGITS
    க்கொள்ள
    2.46
    జ
    2.39
     rato
    2.39
    NonQuery
    2.17
    тира
    2.14
     برابر
    2.14
    енча
    2.09
    izumab
    2.09
    ა
    2.08
     IndexPath
    2.08
    Activations Density 0.082%

    No Known Activations