© 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. 23738
    Prev
    Next
    INDEX
    Explanations

    news publication names

    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
     nei
    -0.90
    Urgent
    -0.88
    合わない
    -0.86
     olvides
    -0.82
     personne
    -0.82
    是我的
    -0.82
     instala
    -0.80
     dado
    -0.80
     futures
    -0.79
    藁
    -0.78
    POSITIVE LOGITS
     Washington
    1.06
     Guardian
    1.00
     Sun
    0.85
    washington
    0.85
    Guardian
    0.84
     Independent
    0.84
     Hindu
    0.83
    Mary
    0.82
    武
    0.81
    Conversation
    0.80
    Activations Density 0.021%

    No Known Activations