© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31889
    Prev
    Next
    INDEX
    Explanations

    Histologic, Tennessee State, Real-time

    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
     ordenado
    -0.89
     erfaring
    -0.80
     Pis
    -0.79
     nonatomic
    -0.77
    ulai
    -0.76
    iros
    -0.75
     Staaten
    -0.75
    toolBar
    -0.74
     playa
    -0.72
     istruzioni
    -0.72
    POSITIVE LOGITS
     crocodiles
    0.71
     Saison
    0.70
     Dyson
    0.69
     glade
    0.67
    办公室
    0.66
    ベッド
    0.66
     Rer
    0.65
     ErrorMessage
    0.65
    typeparam
    0.64
    Ident
    0.64
    Activations Density 0.005%

    No Known Activations