© 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. 35890
    Prev
    Next
    INDEX
    Explanations

    html document end

    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
     fő
    0.45
    Haupt
    0.42
    Annotations
    0.41
    dateTimePicker
    0.41
    Animations
    0.40
    辎
    0.39
    囟
    0.38
    óm
    0.38
     همکاری
    0.38
     haupt
    0.38
    POSITIVE LOGITS
     pygame
    0.43
     serve
    0.42
     offline
    0.42
     sleep
    0.41
     flesh
    0.40
     avsl
    0.40
     n
    0.40
     baza
    0.40
     alimentos
    0.39
     gobern
    0.39
    Activations Density 0.070%

    No Known Activations