© 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. 55659
    Prev
    Next
    INDEX
    Explanations

    Tech Support

    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
    •••
    -0.74
     Studenten
    -0.72
    绿色
    -0.69
    赐
    -0.67
     stereotypes
    -0.67
    •.
    -0.66
    קה
    -0.66
    Simult
    -0.66
    Verde
    -0.65
    ڿ
    -0.65
    POSITIVE LOGITS
     tà
    0.90
     Oren
    0.88
     DSM
    0.87
     soils
    0.79
    くらいの
    0.78
     TAX
    0.78
     soil
    0.77
    CORE
    0.75
     tax
    0.75
     хорошие
    0.75
    Activations Density 0.123%

    No Known Activations