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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 525
    Prev
    Next
    INDEX
    Explanations

    suffix compounds

    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_65k_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
     grande
    1.06
     sm
    1.04
     giudice
    1.02
     quase
    0.99
     fede
    0.98
     fratello
    0.97
     w
    0.96
     la
    0.95
     L
    0.94
     nueve
    0.94
    POSITIVE LOGITS
    graphs
    1.81
    patterns
    1.68
    ograms
    1.68
    matrices
    1.67
    boxes
    1.59
    angements
    1.58
    collisions
    1.56
     trajectories
    1.55
    sensors
    1.54
    stances
    1.53
    Activations Density 1.254%

    No Known Activations