© 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. 22-GEMMASCOPE-RES-131K
    7. 70624
    Prev
    Next
    INDEX
    Explanations

    wait and see

    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
     ännu
    -1.07
    Ң
    -0.93
     särsk
    -0.93
    と思い
    -0.92
    しかも
    -0.90
    UALLY
    -0.90
     scelte
    -0.89
    心脏
    -0.88
    teger
    -0.88
     financeiro
    -0.87
    POSITIVE LOGITS
     potentially
    0.94
     possibility
    0.90
     sabe
    0.89
     ろう
    0.88
     potential
    0.86
     delaying
    0.86
     possible
    0.86
     puis
    0.84
     Possibility
    0.83
     Dabei
    0.83
    Activations Density 0.029%

    No Known Activations