© 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. 84670
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     schönes
    -0.90
     瓦
    -0.89
     einiger
    -0.84
    ຣ
    -0.82
     család
    -0.82
     néhány
    -0.81
     Geschenk
    -0.80
    tiendo
    -0.79
     však
    -0.79
     někter
    -0.79
    POSITIVE LOGITS
     cou
    0.79
     audio
    0.75
     ग
    0.74
    ʰ
    0.73
    clad
    0.73
    dermal
    0.72
     Contr
    0.71
     stri
    0.71
     emergency
    0.70
     corpus
    0.69
    Activations Density 0.015%

    No Known Activations