© 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. 10-GEMMASCOPE-RES-131K
    7. 130301
    Prev
    Next
    INDEX
    Explanations

    colors and shapes

    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_10/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
     Their
    -1.80
     Also
    -1.66
     También
    -1.61
     from
    -1.59
     elevate
    -1.59
     ”
    -1.58
    莛
    -1.56
     Estos
    -1.55
     shabby
    -1.55
     diez
    -1.53
    POSITIVE LOGITS
    isław
    1.81
     dicono
    1.71
     viņ
    1.66
     avendo
    1.64
     endeavors
    1.63
    身后的
    1.60
     fiabilidad
    1.60
    °/
    1.59
     Cryptocurrency
    1.58
    팩
    1.54
    Activations Density 0.177%

    No Known Activations