© 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. 89794
    Prev
    Next
    INDEX
    Explanations

    what is happening or possible

    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
    structing
    -1.17
    cels
    -1.13
    この
    -1.13
     rè
    -1.11
    圖片來源
    -1.09
    ’
    -1.09
     étage
    -1.09
    fordshire
    -1.08
     SIGNIFIC
    -1.08
    ЕН
    -1.07
    POSITIVE LOGITS
     happening
    2.11
     needed
    1.48
     required
    1.36
     going
    1.33
     happened
    1.30
     causing
    1.25
     wrong
    1.23
     happen
    1.23
     there
    1.16
     offered
    1.14
    Activations Density 0.042%

    No Known Activations