© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27038
    Prev
    Next
    INDEX
    Explanations

    recent past 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_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
    现在的
    -1.31
     nächsten
    -1.13
    $("#
    -1.08
    Кто
    -1.02
     now
    -1.01
    äu
    -1.01
    毎年
    -0.98
    ātu
    -0.97
     prado
    -0.97
    menin
    -0.97
    POSITIVE LOGITS
     last
    3.44
     yesterday
    3.06
     recently
    2.70
     earlier
    2.53
     during
    2.16
     recientemente
    1.94
     recent
    1.90
     recentemente
    1.81
     previously
    1.78
     previous
    1.75
    Activations Density 0.170%

    No Known Activations