© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    wife or spouse personal address

    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
    ļa
    1.01
    anyone
    0.94
    akal
    0.93
    anything
    0.93
    ख़
    0.92
    enderita
    0.91
     fickle
    0.90
    {\$
    0.89
    lands
    0.89
    Anything
    0.89
    POSITIVE LOGITS
     以及
    1.56
     serta
    1.45
     그리고
    1.45
     beserta
    1.43
    以及
    1.40
     함께
    1.36
     discussing
    1.36
     ਅਤੇ
    1.35
     together
    1.35
     وكذلك
    1.32
    Activations Density 0.286%

    No Known Activations