© 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. 2423
    Prev
    Next
    INDEX
    Explanations

    local context

    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
     dígitos
    1.20
    čit
    1.04
    Cancellation
    1.02
     wst
    1.00
    枚
    1.00
    bros
    0.97
     keseluruhan
    0.95
    ૢ
    0.93
     десяти
    0.93
    Ded
    0.93
    POSITIVE LOGITS
     locality
    1.43
     neighbourhood
    1.39
     район
    1.39
    乡
    1.37
     localities
    1.34
     grassroots
    1.33
     fief
    1.32
     magistrate
    1.32
     villagers
    1.32
     peasant
    1.29
    Activations Density 0.579%

    No Known Activations