© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73673
    Prev
    Next
    INDEX
    Explanations

    names similar to Kemp or Kern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日程
    -0.88
    圖片
    -0.82
    তথ্যসূত্র
    -0.76
     couples
    -0.74
     reticulum
    -0.73
     Mulher
    -0.73
     plano
    -0.72
     serialization
    -0.72
    的气息
    -0.71
     Obre
    -0.71
    POSITIVE LOGITS
    kem
    0.98
    Kem
    0.94
     Kem
    0.94
     kem
    0.83
     Consider
    0.82
    follows
    0.82
     génér
    0.82
     investimentos
    0.81
     müm
    0.79
    whether
    0.78
    Activations Density 0.010%

    No Known Activations