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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    complement, meaning, or refrigerant

    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
    esehatan
    1.64
    etahui
    1.63
    ised
    1.62
    isasi
    1.60
    reetype
    1.60
    (){
    1.59
    टीसी
    1.57
    itie
    1.57
    andang
    1.55
    isio
    1.53
    POSITIVE LOGITS
     prudent
    1.71
     a
    1.69
     optimal
    1.62
     it
    1.60
     an
    1.57
     一个
    1.57
     这是
    1.56
     “
    1.54
     mere
    1.54
     ideal
    1.52
    Activations Density 0.430%

    No Known Activations