© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1969
    Prev
    Next
    INDEX
    Explanations

    sudden extreme emotional states

    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
     Hutt
    1.57
     Dunedin
    1.39
     Kiwi
    1.31
     ANZ
    1.30
     NZ
    1.28
     Hung
    1.26
     Maori
    1.25
     \|_{
    1.23
     आस्ट्रेलिया
    1.22
    NZ
    1.22
    POSITIVE LOGITS
     Nigerians
    2.26
     Nigerian
    2.22
    Nigerian
    2.06
     Nigeria
    2.06
     Lagos
    1.98
    Nigeria
    1.94
     Abuja
    1.90
     Yoruba
    1.88
     Buhari
    1.85
     Anambra
    1.81
    Activations Density 0.223%

    No Known Activations