© 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. 22-GEMMASCOPE-RES-131K
    7. 71313
    Prev
    Next
    INDEX
    Explanations

    asking for advice

    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
     این
    -0.98
    ściej
    -0.93
    いただきました
    -0.93
     sommige
    -0.90
     this
    -0.88
     людям
    -0.88
    頂きました
    -0.87
     нам
    -0.85
     我们
    -0.85
     засто
    -0.84
    POSITIVE LOGITS
     your
    1.65
     you
    1.44
     yours
    1.01
     ваша
    0.93
    Tembelea
    0.91
     jste
    0.91
     خواهد
    0.90
     ваши
    0.88
    GRAF
    0.87
    GRAPHS
    0.87
    Activations Density 0.010%

    No Known Activations