© 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. 65760
    Prev
    Next
    INDEX
    Explanations

    ruby def initialize

    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
    זו
    -0.87
     alignItems
    -0.87
     kuitenkin
    -0.85
    竦
    -0.84
    恁
    -0.82
     Даже
    -0.82
     („
    -0.81
     getAll
    -0.81
     lucr
    -0.81
    COMO
    -0.81
    POSITIVE LOGITS
     self
    2.16
     initialize
    1.64
    self
    1.63
     to
    1.47
     [](
    1.24
    自
    1.24
    Self
    1.23
     each
    1.17
     خود
    1.12
    initialize
    1.12
    Activations Density 0.017%

    No Known Activations