© 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. 4083
    Prev
    Next
    INDEX
    Explanations

    Let [variable] =

    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
    𒂗
    2.89
    𒀀
    2.78
    ଅ
    2.72
    𝑜
    2.69
     CURLOPT
    2.66
     FutureWarning
    2.66
     прока
    2.65
     opcao
    2.64
    !("{:
    2.54
     =,
    2.53
    POSITIVE LOGITS
    mi
    2.30
    gar
    2.24
     overdrive
    1.98
     hatta
    1.95
    je
    1.90
    žena
    1.89
     mang
    1.88
    gang
    1.87
    lden
    1.87
    sam
    1.87
    Activations Density 0.133%

    No Known Activations