© 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. 116602
    Prev
    Next
    INDEX
    Explanations

    programming package references

    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
     Jerusal
    -0.87
    tapis
    -0.86
     maxWidth
    -0.86
     DOUGLAS
    -0.85
    еры
    -0.84
     couper
    -0.84
     blik
    -0.84
    😂😂😂😂
    -0.83
    яна
    -0.83
     cement
    -0.83
    POSITIVE LOGITS
     sauté
    0.82
    nn
    0.77
    io
    0.77
    Stellar
    0.73
     Negroes
    0.73
     NSE
    0.72
     Jacobi
    0.71
     insurg
    0.71
     J
    0.70
     hawks
    0.70
    Activations Density 0.001%

    No Known Activations