© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101930
    Prev
    Next
    INDEX
    Explanations

    your and you

    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
    indest
    -1.30
     Ketika
    -1.29
    ~~~
    -1.27
    diferentes
    -1.27
    lllllllll
    -1.26
    meldungen
    -1.23
     їх
    -1.20
     graus
    -1.19
     lokale
    -1.17
    lllllll
    -1.17
    POSITIVE LOGITS
     our
    1.63
     Also
    1.40
     it
    1.34
     so
    1.32
     further
    1.31
     also
    1.30
       
    1.23
    菈
    1.15
     նաև
    1.15
    цездатний
    1.14
    Activations Density 0.030%

    No Known Activations