© 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. 7299
    Prev
    Next
    INDEX
    Explanations

    file paths starting with src/

    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
    aner
    -0.78
    yue
    -0.69
    使得
    -0.67
    straw
    -0.66
    숨
    -0.66
     aktyw
    -0.65
     {'
    -0.64
    諗
    -0.63
     Lister
    -0.63
    ല
    -0.63
    POSITIVE LOGITS
     ginge
    0.70
     frapp
    0.67
    VertexArray
    0.66
    該
    0.65
    wirt
    0.65
    Requiem
    0.65
     Rosetta
    0.64
    Lincoln
    0.64
    iment
    0.64
     infan
    0.63
    Activations Density 0.063%

    No Known Activations