© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76245
    Prev
    Next
    INDEX
    Explanations

    things are taken care of

    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
     QE
    -0.84
     Văn
    -0.80
    teinte
    -0.77
     Kard
    -0.77
    އ
    -0.77
     trove
    -0.76
    훼
    -0.75
    arsch
    -0.75
    toft
    -0.75
    দ্ধ
    -0.74
    POSITIVE LOGITS
     handled
    2.36
     care
    2.11
     dealt
    2.09
     handle
    2.02
     handles
    1.99
     handling
    1.76
     cared
    1.76
    处理
    1.74
     cuidar
    1.72
     addressed
    1.68
    Activations Density 0.040%

    No Known Activations