© 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. 232
    Prev
    Next
    INDEX
    Explanations

    anti-christian christmas messages

    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
    РЕ
    2.38
    いる
    2.36
    睍
    2.27
     proporcional
    2.17
    ठमाड
    2.17
    scdn
    2.15
    ७
    2.14
    ｬ
    2.13
    чү
    2.13
    sü
    2.12
    POSITIVE LOGITS
    es
    2.75
    mas
    2.51
    est
    2.29
    жда
    2.26
    ძ
    2.14
    inning
    2.14
    al
    2.13
    een
    2.11
    리는
    2.08
    пись
    2.06
    Activations Density 1.239%

    No Known Activations