© 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. 10-GEMMASCOPE-RES-131K
    7. 42600
    Prev
    Next
    INDEX
    Explanations

    potential [abstract noun]

    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_10/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
     .
    -1.38
     indeb
    -1.33
     romero
    -1.30
     hâte
    -1.28
     учиться
    -1.27
     Bamb
    -1.24
    .}\
    -1.23
     ブラウス
    -1.22
    '},
    -1.22
     Apertura
    -1.20
    POSITIVE LOGITS
     future
    1.70
     further
    1.43
     potential
    1.33
     then
    1.31
     a
    1.31
     end
    1.20
     section
    1.16
     at
    1.12
     just
    1.09
     very
    1.09
    Activations Density 0.217%

    No Known Activations