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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1298
    Prev
    Next
    INDEX
    Explanations

    medical and legal professional advice

    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
    о
    0.75
     pomp
    0.73
     política
    0.73
    оні
    0.72
     borrar
    0.72
    теше
    0.70
     suma
    0.70
     याचिका
    0.70
    ดิจ
    0.69
    oretical
    0.68
    POSITIVE LOGITS
    s
    1.00
    y
    0.73
     રીતે
    0.73
    mente
    0.68
    ized
    0.65
    IZED
    0.65
    idad
    0.64
    niają
    0.63
    ्स
    0.62
     ভাবে
    0.60
    Activations Density 0.224%

    No Known Activations