© 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. 110821
    Prev
    Next
    INDEX
    Explanations

    Free

    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
     suporte
    -1.14
     chamado
    -1.01
     foster
    -0.96
    冧
    -0.95
    𝔴
    -0.94
     proti
    -0.93
     preço
    -0.93
    先の
    -0.91
     bleak
    -0.89
     アウター
    -0.88
    POSITIVE LOGITS
     Free
    1.80
    bie
    1.70
    bies
    1.62
    🆓
    1.60
    free
    1.49
    Free
    1.48
    zers
    1.34
    will
    1.27
    BIE
    1.27
     free
    1.23
    Activations Density 0.082%

    No Known Activations