© 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. 95573
    Prev
    Next
    INDEX
    Explanations

    things known or learned previously

    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
     nachfol
    -1.22
     alcuni
    -1.08
     alcune
    -0.98
     attirer
    -0.98
     accompagner
    -0.97
    Psico
    -0.94
     костюм
    -0.94
    fotograf
    -0.94
     tourner
    -0.91
     заметил
    -0.91
    POSITIVE LOGITS
     previously
    1.75
     теперь
    1.56
     earlier
    1.55
     already
    1.53
     now
    1.34
     अब
    1.34
     we
    1.33
     bereits
    1.30
     już
    1.27
     již
    1.27
    Activations Density 0.030%

    No Known Activations