© 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-16K
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    feeling when

    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_16k_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
    佃
    0.45
     stirring
    0.43
     prank
    0.41
    PPT
    0.41
    animate
    0.40
    HA
    0.40
    anim
    0.40
     portability
    0.39
     chronological
    0.39
    安
    0.38
    POSITIVE LOGITS
     jsme
    0.57
    本書
    0.52
     tohoto
    0.50
     utilizz
    0.47
     nossos
    0.46
    Dieses
    0.46
    rollerskates
    0.45
    hingga
    0.45
     ImageData
    0.45
     combien
    0.45
    Activations Density 0.015%

    No Known Activations