© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    measurement, calculation, testing, research

    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_65k_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
    s
    0.79
     supposedly
    0.75
     your
    0.74
    ️
    0.74
     little
    0.71
     people
    0.71
     heaven
    0.70
    house
    0.70
     remember
    0.69
    ों
    0.69
    POSITIVE LOGITS
     elytris
    1.01
     medición
    0.98
     Одна
    0.98
     Д
    0.95
     (,
    0.93
     Се
    0.92
     П
    0.90
     či
    0.90
     Э
    0.89
     млрд
    0.89
    Activations Density 0.000%

    No Known Activations