© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2006
    Prev
    Next
    INDEX
    Explanations

    guide through process

    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_17_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
    了出来
    1.06
    慫
    1.06
     استاذ
    1.05
    帮忙
    1.04
    ござい
    1.02
     เพราะ
    1.00
     przypad
    1.00
     też
    1.00
    もあり
    0.99
    ございます
    0.98
    POSITIVE LOGITS
    actual
    0.82
    ’
    0.79
    perception
    0.75
    self
    0.74
    maximizing
    0.74
    ның
    0.72
    visual
    0.72
     perception
    0.72
    normal
    0.72
    aking
    0.72
    Activations Density 0.318%

    No Known Activations