© 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. 80768
    Prev
    Next
    INDEX
    Explanations

    words and vocabulary

    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
    WithFormat
    -0.70
     Energía
    -0.69
    ケーキ
    -0.69
     пом
    -0.68
    deti
    -0.68
     Transporte
    -0.67
    ńskich
    -0.67
    insch
    -0.67
     LIGHTS
    -0.65
    lights
    -0.64
    POSITIVE LOGITS
     vocabulary
    1.69
     vocab
    1.60
    vocab
    1.59
     dictionary
    1.30
    vocabulary
    1.24
    Vocab
    1.23
    Vocabulary
    1.16
     Vo
    1.16
     Vocabulary
    1.14
    dictionary
    1.13
    Activations Density 0.013%

    No Known Activations