© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12207
    Prev
    Next
    INDEX
    Explanations

    car makes and models

    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
     arquitetura
    -1.27
     renowned
    -1.13
     dreadful
    -1.08
     verhind
    -1.08
     gigantic
    -1.06
     terrific
    -1.05
     startling
    -1.05
     certamente
    -1.05
     famed
    -1.05
     dreary
    -1.03
    POSITIVE LOGITS
     with
    1.30
    Gön
    1.06
     Recently
    0.93
     overtly
    0.92
    phous
    0.85
    ၄
    0.85
     that
    0.85
     señor
    0.85
     Completely
    0.84
     blatantly
    0.83
    Activations Density 0.029%

    No Known Activations