© 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. 48336
    Prev
    Next
    INDEX
    Explanations

    stripHTML doctypesupervision

    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
    डा
    -0.90
    Pautan
    -0.89
    𝑙
    -0.79
    尤
    -0.78
    ayage
    -0.78
    falz
    -0.77
    posito
    -0.76
     keç
    -0.75
     الشب
    -0.74
     vermel
    -0.73
    POSITIVE LOGITS
     Stri
    0.85
     stripes
    0.84
    看的
    0.82
     Stripe
    0.77
     spacer
    0.75
     STR
    0.75
     stripe
    0.73
    …？
    0.72
     REQUIREMENTS
    0.71
    监督
    0.71
    Activations Density 0.008%

    No Known Activations