© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14371
    Prev
    Next
    INDEX
    Explanations

    owe anyone

    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
     형
    1.70
    ار
    1.67
     Sandbox
    1.59
     던
    1.59
    心的
    1.58
    VERTISING
    1.57
    딪
    1.55
     عظ
    1.51
     kenn
    1.50
    獭
    1.48
    POSITIVE LOGITS
     competenze
    1.80
     नियामक
    1.73
    लया
    1.70
     instrucciones
    1.69
    htar
    1.67
     proceso
    1.66
    RE
    1.66
     гэта
    1.61
     Directive
    1.61
     apenas
    1.61
    Activations Density 0.033%

    No Known Activations