© 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. 10-GEMMASCOPE-RES-131K
    4. 104044
    Prev
    Next
    INDEX
    Explanations

    negative life events

    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
     şeyler
    -1.52
     zároveň
    -1.46
     максимально
    -1.46
    杳
    -1.37
    unesse
    -1.37
     similaires
    -1.31
    ränk
    -1.28
     nyní
    -1.27
     максима
    -1.27
     zvlá
    -1.27
    POSITIVE LOGITS
     two
    1.76
    two
    1.66
    msford
    1.53
     by
    1.52
    your
    1.45
    even
    1.39
    three
    1.38
     four
    1.38
    )});
    1.38
     Polsek
    1.33
    Activations Density 0.000%

    No Known Activations