© 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. 59833
    Prev
    Next
    INDEX
    Explanations

    introducing next topic

    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
    alucía
    -0.89
    formatie
    -0.84
     Stephan
    -0.83
     Auth
    -0.82
     envoyer
    -0.82
    namientos
    -0.82
    writes
    -0.81
    mdan
    -0.80
     termes
    -0.79
    getenv
    -0.79
    POSITIVE LOGITS
     briefly
    2.14
     brief
    1.38
     mention
    1.34
     Briefly
    1.28
    brief
    1.24
     brevemente
    1.23
     now
    1.23
     dealt
    1.16
    Brief
    1.13
     consideration
    1.08
    Activations Density 0.017%

    No Known Activations