© 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. 2045
    Prev
    Next
    INDEX
    Explanations

    word details count

    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
     ciudades
    1.35
     Routes
    1.33
    🗺
    1.30
     Map
    1.25
    Agricult
    1.21
    ItemList
    1.18
    Map
    1.17
     Sprachen
    1.17
    Maps
    1.16
    Petrol
    1.16
    POSITIVE LOGITS
     회
    0.93
     incision
    0.90
     thickened
    0.89
    rete
    0.88
     filet
    0.87
     initiate
    0.86
     flexion
    0.85
     fibroblasts
    0.85
     rebound
    0.85
    緹
    0.84
    Activations Density 0.104%

    No Known Activations