© 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. 86987
    Prev
    Next
    INDEX
    Explanations

    picking, plucking, pinching

    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
     unparalleled
    -1.61
     wants
    -1.34
     subtly
    -1.33
     solidly
    -1.30
     esquina
    -1.29
     diferente
    -1.28
     supremely
    -1.27
     should
    -1.27
     might
    -1.26
     могла
    -1.25
    POSITIVE LOGITS
    selecting
    1.47
    six
    1.41
     reflexiones
    1.40
     jenen
    1.36
    AndPassword
    1.34
     упомина
    1.34
    acheteur
    1.32
    sizable
    1.30
     verdaderas
    1.30
    takes
    1.28
    Activations Density 0.039%

    No Known Activations