© 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. 22-GEMMASCOPE-RES-131K
    4. 40274
    Prev
    Next
    INDEX
    Explanations

    mostly Latino, majority coming

    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_22/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
    stoel
    -1.07
    ⇆
    -1.06
     puissiez
    -1.05
    噏
    -1.05
    gradable
    -1.02
    ختلف
    -1.02
    antism
    -0.99
     normaal
    -0.99
    
    -0.99
     ahogy
    -0.98
    POSITIVE LOGITS
     from
    2.08
     именно
    1.31
     those
    1.28
     in
    1.20
     small
    1.09
     dotyczy
    1.09
     từ
    1.02
     people
    1.00
     of
    1.00
     young
    0.99
    Activations Density 0.078%

    No Known Activations