© 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. 7-GEMMASCOPE-2-RES-16K
    7. 768
    Prev
    Next
    INDEX
    Explanations

    ever very so

    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_7_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
    ာ
    0.77
    𝙘
    0.74
    ים
    0.73
     couches
    0.71
    ზრ
    0.70
    스크
    0.69
    existent
    0.69
    𝙢
    0.68
    럽
    0.67
    𝙚
    0.67
    POSITIVE LOGITS
     tidak
    1.03
     nggak
    0.94
     presidenta
    0.90
     personalizado
    0.88
     começou
    0.85
     venido
    0.85
     Tidak
    0.84
     ilusión
    0.84
     comenzó
    0.83
     heeft
    0.83
    Activations Density 0.800%

    No Known Activations