© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76307
    Prev
    Next
    INDEX
    Explanations

    revered, renowned, newly, discover

    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
     laine
    -1.51
    !(
    -1.39
     even
    -1.39
     flesta
    -1.38
     statut
    -1.35
     satte
    -1.34
    :+:
    -1.33
     augus
    -1.32
     lilla
    -1.32
     mär
    -1.30
    POSITIVE LOGITS
    .
    1.73
     jednej
    1.59
     nazy
    1.52
     revered
    1.52
     renowned
    1.47
     odkry
    1.45
     parere
    1.42
     hugely
    1.38
    怎么做
    1.37
     nowej
    1.36
    Activations Density 0.002%

    No Known Activations