© 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. 47895
    Prev
    Next
    INDEX
    Explanations

    here you go

    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
    discrete
    -0.77
    irmish
    -0.75
     siff
    -0.75
    dibu
    -0.74
     Discrete
    -0.74
     departe
    -0.73
     discrete
    -0.72
     stai
    -0.71
     Mediat
    -0.71
     »)
    -0.69
    POSITIVE LOGITS
     swine
    0.74
    ėje
    0.72
     go
    0.71
     manifold
    0.71
     raíces
    0.70
    êche
    0.70
     garnered
    0.69
    回避
    0.68
    /*
    0.67
     brings
    0.66
    Activations Density 0.048%

    No Known Activations