© 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-65K
    7. 40513
    Prev
    Next
    INDEX
    Explanations

    specific keywords and their continuations

    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
     recettes
    0.54
     asia
    0.51
     coincident
    0.48
     i
    0.48
    0.48
     известен
    0.48
     ie
    0.47
     winkel
    0.47
     Riy
    0.46
     Tro
    0.46
    POSITIVE LOGITS
    ץ
    0.56
    тна
    0.47
    ImgBoard
    0.47
    搆
    0.44
    hedron
    0.44
    OnInit
    0.44
     用户
    0.44
    敞
    0.43
    酺
    0.43
    ম্বা
    0.43
    Activations Density 0.002%

    No Known Activations