Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 187
    Prev
    Next
    INDEX
    Explanations

    academic subjects and qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    0.56
     (
    0.54
     sill
    0.50
     ting
    0.49
     w
    0.49
     D
    0.48
    ↵↵
    0.46
     l
    0.45
     W
    0.45
     ex
    0.45
    POSITIVE LOGITS
    goài
    1.08
    iduría
    1.05
    iftoire
    1.02
    direccion
    1.02
    количество
    0.99
    cantidad
    0.99
    acciones
    0.93
    resión
    0.92
    certificado
    0.91
    seleccion
    0.91
    Activations Density 0.620%

    No Known Activations