© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105917
    Prev
    Next
    INDEX
    Explanations

    physical features and technical terms

    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_16_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
    坸
    0.46
    勂
    0.46
    物品
    0.46
     thumbnail
    0.45
     thumbnails
    0.44
    儿童
    0.44
     όλα
    0.43
    芢
    0.42
    开车
    0.42
    䀘
    0.42
    POSITIVE LOGITS
    ،
    0.55
    ↵↵
    0.54
    proper
    0.53
      
    0.52
    phase
    0.48
    plastic
    0.48
    kaan
    0.48
    の種類
    0.48
     Acc
    0.48
    bagian
    0.48
    Activations Density 0.000%

    No Known Activations