© 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. 48084
    Prev
    Next
    INDEX
    Explanations

    academic, programming, or proper nouns

    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
    ፣
    -0.81
     moze
    -0.77
    Wik
    -0.73
    ვ
    -0.72
     membranes
    -0.72
    Homework
    -0.71
    kka
    -0.71
     diversidad
    -0.71
    meo
    -0.69
     accountId
    -0.69
    POSITIVE LOGITS
     компо
    0.74
     Introducing
    0.71
     sammeln
    0.66
     компонентов
    0.66
    être
    0.65
    nia
    0.65
     Majesté
    0.65
    応援
    0.64
     ANSI
    0.64
    Introducing
    0.63
    Activations Density 0.032%

    No Known Activations