© 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. 75934
    Prev
    Next
    INDEX
    Explanations

    future when

    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
    tamientos
    -1.27
     بداية
    -1.25
     telah
    -1.21
     parfois
    -1.15
    immediately
    -1.12
     depuis
    -1.09
     rése
    -1.07
    couldn
    -1.05
    often
    -1.04
    beginning
    -1.04
    POSITIVE LOGITS
     eventually
    2.16
     hopefully
    2.06
     next
    1.95
     get
    1.70
     Eventually
    1.70
     gets
    1.70
    Eventually
    1.68
     someday
    1.63
     comes
    1.57
     eventual
    1.53
    Activations Density 0.031%

    No Known Activations