© 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. 10-GEMMASCOPE-RES-131K
    7. 119879
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_10/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
    ᚔ
    -3.17
    嫫
    -3.05
    
    -2.91
    ܜ
    -2.75
    би
    -2.58
     entsprechende
    -2.48
    满是
    -2.47
    ꈊ
    -2.42
     */
    -2.41
    )}]{
    -2.41
    POSITIVE LOGITS
    s
    2.81
    ]
    2.67
    P
    2.56
    ON
    2.52
    .
    2.50
    ஂ
    2.50
    M
    2.42
     廠
    2.36
    R
    2.30
     Because
    2.25
    Activations Density 0.005%

    No Known Activations