© 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-16K
    7. 1263
    Prev
    Next
    INDEX
    Explanations

    market dynamics

    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
     tampa
    1.71
     Tampa
    1.70
     lom
    1.64
     berühm
    1.62
     persone
    1.61
     ___
    1.61
     __
    1.60
     Nome
    1.58
     Pron
    1.58
     _____
    1.58
    POSITIVE LOGITS
    ymmetries
    2.08
     perturbations
    2.02
    ogeneities
    1.89
     perturbation
    1.87
    oxylated
    1.85
    roweak
    1.82
    manifolds
    1.82
     tensors
    1.80
    ochastic
    1.77
    urbance
    1.74
    Activations Density 0.635%

    No Known Activations