© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3011
    Prev
    Next
    INDEX
    Explanations

    software development and version control

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝑠
    1.77
    Sunflower
    1.76
    सँग
    1.74
    γη
    1.69
    ધા
    1.69
    сі
    1.69
    Ꮖ
    1.64
    subMenu
    1.64
     potens
    1.61
     அமை
    1.60
    POSITIVE LOGITS
     committed
    1.59
     breached
    1.54
     GitHub
    1.48
     proteomics
    1.47
     /><
    1.44
     Committed
    1.44
     Repo
    1.43
     Rapport
    1.41
     COMMIT
    1.41
     Marne
    1.39
    Activations Density 0.245%

    No Known Activations