© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78651
    Prev
    Next
    INDEX
    Explanations

    inflate, inflated, inflation

    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
     Judo
    -0.74
    Numerade
    -0.71
    愬
    -0.71
     Firewall
    -0.71
     kitab
    -0.70
    keny
    -0.69
     Hacking
    -0.67
    leans
    -0.66
    emeni
    -0.66
     messy
    -0.65
    POSITIVE LOGITS
     inflate
    4.75
     inflated
    4.47
     inflation
    4.31
    inflate
    3.91
     inflatable
    3.77
    inflated
    3.72
    Infl
    3.70
     Inflation
    3.55
    inflation
    3.52
     Inflate
    3.50
    Activations Density 0.108%

    No Known Activations