© 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. 76565
    Prev
    Next
    INDEX
    Explanations

    CSS specifications and 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
    延续
    -0.89
     하나
    -0.88
    спомина
    -0.87
    they
    -0.83
    ",
    -0.82
     ammonium
    -0.81
    antor
    -0.80
     дітей
    -0.79
     majorité
    -0.79
    Volatile
    -0.78
    POSITIVE LOGITS
     selector
    1.04
    rs
    0.96
     şeyi
    0.96
    煸
    0.94
     rookie
    0.92
    igheid
    0.89
    nano
    0.89
    ILERS
    0.87
    cass
    0.87
     rules
    0.87
    Activations Density 0.017%

    No Known Activations