© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3492
    Prev
    Next
    INDEX
    Explanations

    Swedish muscles animation

    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
    θ
    0.48
    ন
    0.43
    定义
    0.40
    参数
    0.39
    细
    0.39
    όν
    0.38
    σ
    0.38
    ίσ
    0.37
    άλ
    0.37
    ନ୍ଦ
    0.37
    POSITIVE LOGITS
     quel
    0.45
     relevante
    0.44
     nepot
    0.44
     inept
    0.44
     quell
    0.41
     cognitiva
    0.41
     estatal
    0.41
     jaga
    0.41
     potencia
    0.40
     venge
    0.40
    Activations Density 1.122%

    No Known Activations