© 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. 34703
    Prev
    Next
    INDEX
    Explanations

    directory paths and code structures

    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
     helicopter
    -0.67
     प्रदान
    -0.65
     printer
    -0.64
    iting
    -0.64
     PRINT
    -0.63
    ennom
    -0.63
     Chapin
    -0.63
    matric
    -0.63
    нная
    -0.62
     Sui
    -0.62
    POSITIVE LOGITS
    ônica
    0.71
    gebras
    0.70
    槟
    0.69
     ді
    0.68
     denominated
    0.68
     Samos
    0.67
    wini
    0.66
    лися
    0.66
     главе
    0.64
    pal
    0.63
    Activations Density 0.083%

    No Known Activations