© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36302
    Prev
    Next
    INDEX
    Explanations

    health and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    嫄
    0.45
     in
    0.43
     पाएंगे
    0.41
     Mitte
    0.41
     Städ
    0.41
    辽
    0.41
     فانه
    0.40
     Nickel
    0.40
     Studie
    0.40
    مد
    0.40
    POSITIVE LOGITS
    p
    0.54
    m
    0.53
    im
    0.46
     zombies
    0.44
    ISTS
    0.43
     ethers
    0.43
     rodents
    0.43
     pigeons
    0.42
    Capacity
    0.41
    io
    0.40
    Activations Density 0.001%

    No Known Activations