© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4898
    Prev
    Next
    INDEX
    Explanations

    rpg, game, text, doors

    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
    k
    0.90
    all
    0.90
      
    0.89
    ly
    0.87
    anat
    0.86
     север
    0.83
       
    0.80
    не
    0.80
    с
    0.79
    man
    0.78
    POSITIVE LOGITS
    <unused1941>
    1.45
     réseaux
    1.29
     vattum
    1.27
     DBox
    1.22
     productColor
    1.19
     calon
    1.17
     Dropbox
    1.14
     coloquei
    1.12
    <unused1345>
    1.12
     hyperparameters
    1.11
    Activations Density 13.346%

    No Known Activations