© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12931
    Prev
    Next
    INDEX
    Explanations

    culture, penetration, providers, punctuation

    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_262k_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
    generalized
    0.23
    ან
    0.22
     अंतर्गत
    0.22
    אן
    0.21
     Віль
    0.21
     общей
    0.21
    ט
    0.21
    欢迎
    0.20
    über
    0.20
     مجموعة
    0.20
    POSITIVE LOGITS
     đảm
    0.26
     faciles
    0.24
     steels
    0.24
     SNPs
    0.24
     soo
    0.22
     upperBound
    0.22
     ensuring
    0.22
     annulus
    0.22
     bottoms
    0.22
     sockfd
    0.21
    Activations Density 0.242%

    No Known Activations