© 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. 116881
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    ይ
    -0.75
    groupBy
    -0.64
     tarafından
    -0.63
    onion
    -0.62
    redmi
    -0.62
     Spas
    -0.62
    “-
    -0.61
     reset
    -0.61
     ис
    -0.61
    ädie
    -0.61
    POSITIVE LOGITS
     faked
    0.73
     faking
    0.71
     Cow
    0.66
    分离
    0.65
     configurable
    0.63
     fakes
    0.63
    hm
    0.62
     measles
    0.61
     Faw
    0.60
    走行
    0.60
    Activations Density 0.086%

    No Known Activations