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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23637
    Prev
    Next
    INDEX
    Explanations

    data-dependent, cuts, 2024

    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
     NFTs
    0.66
     metaverse
    0.60
    🥲
    0.59
    🥹
    0.59
     TikTok
    0.54
     ChatGPT
    0.54
    🫶
    0.54
    🫡
    0.52
    🥺
    0.51
     NFT
    0.50
    POSITIVE LOGITS
    UInteger
    0.43
    
    0.40
     พิจิก
    0.39
    篦
    0.39
     pinion
    0.38
     myel
    0.38
     अड
    0.38
    cusson
    0.38
    핀
    0.37
     Cull
    0.37
    Activations Density 0.116%

    No Known Activations