© 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. 8726
    Prev
    Next
    INDEX
    Explanations

    phrase "you like"

    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
    ُّ
    1.99
    ¡
    1.97
    cheerful
    1.96
    wonderful
    1.89
     cheerful
    1.84
    ّ
    1.84
    delicious
    1.83
    ُ
    1.77
     آ
    1.74
    pleasant
    1.73
    POSITIVE LOGITS
     mesmos
    1.47
     olhando
    1.39
     variabili
    1.37
     gestire
    1.37
     gerar
    1.36
     generando
    1.32
     mesmas
    1.32
     mismas
    1.31
     posisi
    1.28
     riport
    1.28
    Activations Density 0.101%

    No Known Activations