© 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. 83025
    Prev
    Next
    INDEX
    Explanations

    authentication email addresses

    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
     iko
    -0.97
     tslint
    -0.88
     rute
    -0.87
     hoga
    -0.80
     imago
    -0.77
     until
    -0.75
     Trump
    -0.74
     vant
    -0.72
     kase
    -0.71
     yaka
    -0.70
    POSITIVE LOGITS
    setSelected
    0.95
    //!
    0.93
    gpt
    0.92
    peutic
    0.91
    ONIC
    0.89
     WHILE
    0.88
     könig
    0.88
    TGF
    0.87
    athies
    0.87
    schutz
    0.87
    Activations Density 0.003%

    No Known Activations