© 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. 84188
    Prev
    Next
    INDEX
    Explanations

    . or org

    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
     以
    -0.72
    urel
    -0.65
    Relative
    -0.65
    morning
    -0.64
     Anreg
    -0.63
     relativi
    -0.63
     semn
    -0.63
    进步
    -0.63
    мель
    -0.62
    vertical
    -0.62
    POSITIVE LOGITS
    folia
    0.68
     festen
    0.66
    iaus
    0.65
     Pointe
    0.65
     باشه
    0.63
     EDP
    0.62
    Mish
    0.62
     Spectra
    0.62
     disposi
    0.62
     Jacoby
    0.62
    Activations Density 0.059%

    No Known Activations