© 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. 56087
    Prev
    Next
    INDEX
    Explanations

    school of academic fields

    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
    後に
    -0.90
    一定会
    -0.89
    就去
    -0.89
    擽
    -0.87
    などを
    -0.87
     delantero
    -0.84
    却被
    -0.83
     recev
    -0.82
    唷
    -0.82
     decidiu
    -0.82
    POSITIVE LOGITS
     medicine
    1.14
     Medicine
    1.08
     Engineering
    0.98
    Medicine
    0.90
     on
    0.84
     yeah
    0.83
    Мекси
    0.79
    jąca
    0.79
     Law
    0.78
     engineering
    0.78
    Activations Density 0.011%

    No Known Activations