© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2250
    Prev
    Next
    INDEX
    Explanations

    places ending in nants)

    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_65k_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
     totiž
    0.97
     Infatti
    0.91
     seura
    0.87
     kuitenkin
    0.87
    のを
    0.85
     actually
    0.85
     namelijk
    0.84
     Qxg
    0.83
     firstly
    0.82
    actually
    0.82
    POSITIVE LOGITS
     etc
    1.65
     ইত্যাদি
    1.63
     Etc
    1.42
     প্রমুখ
    1.39
    etc
    1.34
     প্রভৃতি
    1.31
     इत्यादि
    1.31
     тощо
    1.30
     इत्यादी
    1.29
     প্রভৃতির
    1.26
    Activations Density 2.340%

    No Known Activations