© 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. 34-GEMMASCOPE-RES-131K
    7. 4408
    Prev
    Next
    INDEX
    Explanations

    titles followed by names

    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
     możesz
    -0.75
    wheat
    -0.74
     tenho
    -0.74
     тебя
    -0.73
     klap
    -0.72
    tyk
    -0.70
    mitteln
    -0.69
    员工
    -0.68
    Dichloro
    -0.68
    ֵ
    -0.68
    POSITIVE LOGITS
     Mr
    5.69
    Mr
    4.78
     Ms
    3.75
     mr
    3.25
     Mrs
    3.17
    Ms
    3.14
    mr
    2.81
     آقای
    2.70
    Mrs
    2.64
     Messrs
    2.56
    Activations Density 0.055%

    No Known Activations