© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31970
    Prev
    Next
    INDEX
    Explanations

    expresses strong preference or sentiment

    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
     różne
    -1.23
    Ḫ
    -1.07
     различных
    -1.05
     разных
    -1.05
     многих
    -1.05
     veľmi
    -1.01
    さき
    -1.00
     여러
    -1.00
     vários
    -0.98
     históricas
    -0.97
    POSITIVE LOGITS
     a
    2.78
     good
    1.87
     freshly
    1.57
     an
    1.56
     clássico
    1.45
     having
    1.33
    good
    1.29
     fresh
    1.21
     verdadeiro
    1.21
     хоро
    1.20
    Activations Density 0.051%

    No Known Activations