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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2362
    Prev
    Next
    INDEX
    Explanations

    official website URLs

    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
     وتع
    1.71
    evaluated
    1.61
     dropped
    1.60
     softened
    1.56
     phased
    1.55
    ̆
    1.55
     penetrating
    1.55
    ց
    1.54
     picked
    1.54
     o
    1.52
    POSITIVE LOGITS
    www
    2.28
    kirche
    2.21
    nbhost
    2.04
     pergunt
    1.98
    佥
    1.94
     ferram
    1.94
     tercero
    1.90
    ⁦
    1.88
     ciências
    1.87
     halaman
    1.85
    Activations Density 0.016%

    No Known Activations