© 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-16K
    7. 1439
    Prev
    Next
    INDEX
    Explanations

    enclosing math answers with \boxed{}

    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
     SMC
    1.15
     Island
    1.13
     ठाकुर
    1.08
     alps
    1.07
     일본
    1.07
     japon
    1.07
     伊
    1.05
     핵심
    1.05
     Tosh
    1.03
     Ramos
    1.03
    POSITIVE LOGITS
    ֽ
    1.08
    Secondly
    0.98
     অতএব
    0.97
    Folders
    0.96
     Secondly
    0.93
    Therefore
    0.91
     maneras
    0.91
    ENTY
    0.86
     polinomio
    0.86
    Quadr
    0.85
    Activations Density 0.190%

    No Known Activations