© 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. 53912
    Prev
    Next
    INDEX
    Explanations

    lack of something

    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
     incredi
    -1.29
     POSSIBLE
    -1.28
    warzys
    -1.24
    thday
    -1.23
    bleau
    -1.20
    ⭐⭐⭐⭐
    -1.20
    
    -1.19
     impecable
    -1.17
     dific
    -1.16
    ícias
    -1.16
    POSITIVE LOGITS
     sufficient
    2.55
     adequate
    2.34
     any
    2.20
     suitable
    2.17
     available
    1.95
     proper
    1.94
     information
    1.84
     appropriate
    1.84
     enough
    1.80
     funds
    1.80
    Activations Density 0.031%

    No Known Activations