© 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. 6995
    Prev
    Next
    INDEX
    Explanations

    licensed under

    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
     seem
    -1.27
     seems
    -1.13
     Seems
    -0.98
    Seems
    -0.98
     seeming
    -0.94
     parece
    -0.85
    ijnt
    -0.84
    seems
    -0.79
    似乎
    -0.77
     parecen
    -0.75
    POSITIVE LOGITS
     paper
    1.92
     papers
    1.75
     Paper
    1.73
    Paper
    1.71
    PAPER
    1.59
     PAPER
    1.44
     Papers
    1.40
    paper
    1.40
    papers
    1.37
    Papers
    1.24
    Activations Density 0.005%

    No Known Activations