© 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. 76133
    Prev
    Next
    INDEX
    Explanations

    company names and labels

    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
    Läs
    -1.02
    嗒
    -1.00
     письмо
    -0.98
    💁
    -0.98
    пион
    -0.97
     Password
    -0.93
    velser
    -0.92
     gyerme
    -0.92
    strateg
    -0.92
    thebibliography
    -0.92
    POSITIVE LOGITS
     name
    1.21
     matched
    1.12
     matching
    1.08
     ergänzt
    1.07
     lookup
    1.05
     cleaned
    1.01
     curated
    1.00
     бампер
    1.00
     fuzzy
    1.00
     matches
    1.00
    Activations Density 0.085%

    No Known Activations