© 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. 73660
    Prev
    Next
    INDEX
    Explanations

    ment markers

    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
     from
    -1.06
     savu
    -1.05
     or
    -1.01
    bürger
    -1.00
     Autres
    -0.94
     without
    -0.92
    вір
    -0.90
    ESL
    -0.89
    觑
    -0.87
     ролях
    -0.86
    POSITIVE LOGITS
    というわけで
    1.18
    さてさて
    1.05
     ག
    1.05
    それにしても
    1.05
     reparación
    1.04
    そういえば
    1.02
    了过去
    1.02
    ではでは
    0.99
    それでは
    0.98
     約
    0.97
    Activations Density 0.001%

    No Known Activations