© 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. 73583
    Prev
    Next
    INDEX
    Explanations

    people's past roles leading to gain

    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
     đều
    -0.84
    绯
    -0.80
    erving
    -0.71
    ɧ
    -0.71
     ві
    -0.70
    헙
    -0.70
     chistes
    -0.69
     kekinian
    -0.69
    んだろう
    -0.69
     գ
    -0.69
    POSITIVE LOGITS
     rose
    3.06
     gained
    2.95
    gain
    2.44
     gain
    2.36
     rise
    2.08
    Gain
    2.05
     Gain
    1.95
     gains
    1.88
    rose
    1.84
     gaining
    1.80
    Activations Density 0.163%

    No Known Activations