© 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. 104538
    Prev
    Next
    INDEX
    Explanations

    your this its

    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
     something
    -1.08
     (;;)
    -1.05
    urface
    -0.99
     quelque
    -0.97
     offrire
    -0.96
    å
    -0.96
    人の
    -0.95
    umerable
    -0.94
    cising
    -0.93
    aday
    -0.92
    POSITIVE LOGITS
     that
    1.27
     from
    1.18
     також
    1.08
    Ѵ
    1.03
    arrings
    1.00
     различни
    0.99
     tidak
    0.98
     are
    0.97
     list
    0.97
     који
    0.96
    Activations Density 0.091%

    No Known Activations