© 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. 22-GEMMASCOPE-RES-131K
    4. 70995
    Prev
    Next
    INDEX
    Explanations

    past hypotheticals and regrets

    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_22/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
     are
    -1.09
    urnya
    -0.94
     आहे
    -0.90
    ありがたい
    -0.87
    egli
    -0.86
     they
    -0.84
     використовувати
    -0.83
     đang
    -0.83
     theyre
    -0.82
     població
    -0.81
    POSITIVE LOGITS
     hubiera
    1.28
     aurait
    1.26
     instead
    1.22
     perhaps
    1.21
     would
    1.16
     gdyby
    1.13
     hätte
    1.12
     hindsight
    1.11
     nếu
    1.08
    あの
    1.06
    Activations Density 0.026%

    No Known Activations