© 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. 6705
    Prev
    Next
    INDEX
    Explanations

    not any

    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
    urization
    -1.20
    rably
    -1.08
     ideale
    -1.06
    
    -1.05
     =>
    
    -1.05
    cobacterium
    -1.05
    AMED
    -1.05
    roduction
    -1.04
     manier
    -1.02
    ologists
    -1.02
    POSITIVE LOGITS
     not
    2.23
     a
    1.62
     already
    1.41
     still
    1.32
     human
    1.30
     kuitenkin
    1.27
     also
    1.19
     only
    1.18
     young
    1.13
     intelligent
    1.12
    Activations Density 0.031%

    No Known Activations