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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9947
    Prev
    Next
    INDEX
    Explanations

    official resources

    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_22_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
     Sag
    1.29
    Sag
    1.22
    sag
    1.22
    麋
    1.20
     Mage
    1.14
    SAG
    1.13
     Quir
    1.13
     Kum
    1.08
     Ghan
    1.08
    藁
    1.07
    POSITIVE LOGITS
     Tennis
    2.94
     tennis
    2.79
    Tennis
    2.67
    tennis
    2.57
     Djokovic
    2.46
    🎾
    2.40
     racquet
    2.22
     Federer
    2.22
     टेनिस
    2.13
     Nadal
    2.13
    Activations Density 0.300%

    No Known Activations