© 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. 33598
    Prev
    Next
    INDEX
    Explanations

    customer service complaints

    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
    uscular
    -0.88
    そのまま
    -0.88
     gusts
    -0.86
    と思って
    -0.86
    crollView
    -0.81
     protesta
    -0.80
     (/
    -0.78
     dramatique
    -0.76
    これに
    -0.76
    PECT
    -0.76
    POSITIVE LOGITS
    promises
    1.20
     promises
    1.13
     fob
    1.12
     response
    1.09
     різних
    1.08
     excuses
    1.08
     responses
    1.08
     promise
    1.01
    cuses
    1.00
     told
    0.98
    Activations Density 0.019%

    No Known Activations