© 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. 60294
    Prev
    Next
    INDEX
    Explanations

    web server or advertisement

    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
    際には
    -1.04
     manifeste
    -0.98
     sûre
    -0.96
    ꪔ
    -0.96
    囫
    -0.96
    сезон
    -0.94
     草莓
    -0.94
    *',
    -0.92
    蹩
    -0.92
    visuel
    -0.90
    POSITIVE LOGITS
     both
    1.27
     especially
    1.08
     what
    1.01
     touted
    0.96
     mainly
    0.91
    .¹
    0.91
     those
    0.91
     always
    0.89
     perpetually
    0.88
     relatively
    0.88
    Activations Density 0.000%

    No Known Activations