© 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. 32740
    Prev
    Next
    INDEX
    Explanations

    or / and

    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
     femelle
    -0.89
     steaks
    -0.84
    早餐
    -0.82
    готовление
    -0.82
     breakfasts
    -0.82
    ódromo
    -0.82
    鹿
    -0.79
    essoal
    -0.76
    救援
    -0.76
     krę
    -0.76
    POSITIVE LOGITS
     choice
    1.85
     either
    1.43
    choice
    1.39
     chosen
    1.35
     choosing
    1.34
     choisi
    1.31
     drink
    1.31
     choices
    1.28
     chooses
    1.27
    choose
    1.26
    Activations Density 0.013%

    No Known Activations