© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14214
    Prev
    Next
    INDEX
    Explanations

    of noun/concept

    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
     COMERC
    -1.09
     NACIONAL
    -1.09
     "");
    
    -1.05
     DOMINGO
    -1.05
     MUNDO
    -1.05
     impuestos
    -1.02
     '@/
    -1.02
    岀
    -1.00
     SANTOS
    -0.97
     TIEMPO
    -0.96
    POSITIVE LOGITS
     of
    1.64
     these
    1.27
     that
    1.27
     and
    1.27
     for
    1.24
     này
    1.21
     These
    1.19
    で見る
    1.09
     from
    1.08
    看了看
    1.07
    Activations Density 0.074%

    No Known Activations