© 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. 10-GEMMASCOPE-RES-131K
    7. 70783
    Prev
    Next
    INDEX
    Explanations

    DSM diagnostic criteria

    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_10/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
     are
    -1.59
    祤
    -1.59
    enablog
    -1.52
    ſſi
    -1.50
     пиво
    -1.50
    gged
    -1.48
    ésult
    -1.45
     savages
    -1.45
     ноябре
    -1.45
    devi
    -1.44
    POSITIVE LOGITS
     manchmal
    1.70
    Now
    1.62
    Sometimes
    1.62
     olvidar
    1.54
     soñar
    1.52
    小朋友
    1.48
    Later
    1.45
     alot
    1.45
     llorar
    1.40
    Ahora
    1.38
    Activations Density 0.047%

    No Known Activations