© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66878
    Prev
    Next
    INDEX
    Explanations

    individuals, professionals, authors

    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_22/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
    ないです
    -1.00
    
    -0.96
     faltar
    -0.93
     parco
    -0.91
     adopted
    -0.90
    ORPG
    -0.90
    símbolo
    -0.90
     論
    -0.90
     allgeme
    -0.89
    ご予約
    -0.88
    POSITIVE LOGITS
    个人
    1.45
     व्यक्ति
    1.45
    個人
    1.37
     personally
    1.32
     personnal
    1.22
    Individual
    1.20
     лично
    1.20
    Personal
    1.20
    individual
    1.16
     personal
    1.13
    Activations Density 0.110%

    No Known Activations