© 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. 73831
    Prev
    Next
    INDEX
    Explanations

    Core tip:

    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
    轰隆
    -1.05
    (){
    -0.96
     stí
    -0.95
     ainsi
    -0.93
     экскур
    -0.93
    轰隆隆
    -0.91
     HasFactory
    -0.90
     Biôgrafia
    -0.89
    angaben
    -0.89
    aaaaa
    -0.88
    POSITIVE LOGITS
     cumbersome
    0.90
    inau
    0.90
     afterwards
    0.84
    zene
    0.84
    arande
    0.83
     Need
    0.82
    だって
    0.82
     chẳng
    0.81
     inadequate
    0.80
    Felipe
    0.80
    Activations Density 0.003%

    No Known Activations