© 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-16K
    7. 9067
    Prev
    Next
    INDEX
    Explanations

    for loops with index i

    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
    串
    1.47
    生命
    1.46
     życia
    1.46
     única
    1.45
     próxima
    1.43
     egyszer
    1.42
     MyRegisterClass
    1.40
     ζ
    1.39
     expresión
    1.37
     estudiante
    1.37
    POSITIVE LOGITS
    landing
    1.35
    oufl
    1.28
    stuffs
    1.25
     pottery
    1.21
    opener
    1.20
    necked
    1.19
     preexisting
    1.18
     gymnastics
    1.18
    previous
    1.17
    imbledon
    1.17
    Activations Density 0.005%

    No Known Activations