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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36464
    Prev
    Next
    INDEX
    Explanations

    modern slang

    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
     pertanto
    0.43
    мента
    0.41
     вид
    0.41
    ници
    0.39
     তাতে
    0.39
     면
    0.39
     ships
    0.39
     cambiamento
    0.39
     incol
    0.38
     fn
    0.38
    POSITIVE LOGITS
    ៉ុ
    0.57
    ARN
    0.54
    JPEG
    0.48
    ir
    0.46
    ESPN
    0.46
    ASP
    0.45
    km
    0.44
    樖
    0.44
    RAM
    0.44
    IRD
    0.44
    Activations Density 0.025%

    No Known Activations