© 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. 65430
    Prev
    Next
    INDEX
    Explanations

    names followed by awards

    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
     préciser
    -1.02
     социаль
    -0.90
     Simult
    -0.89
     MISSION
    -0.88
     marseille
    -0.88
    pherds
    -0.87
    äk
    -0.87
     georgia
    -0.85
     الكه
    -0.85
     HARVARD
    -0.85
    POSITIVE LOGITS
     Award
    2.41
     Awards
    2.09
     awards
    2.08
     award
    2.08
    Award
    1.78
    Awards
    1.66
     Prize
    1.59
     prestigious
    1.58
     awarded
    1.52
     prize
    1.50
    Activations Density 0.047%

    No Known Activations