© 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. 29119
    Prev
    Next
    INDEX
    Explanations

    who you are or I am

    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
    ll
    -1.44
    糁
    -1.40
     acoged
    -1.35
    érieurs
    -1.34
     ſtand
    -1.33
     peligros
    -1.30
     nessa
    -1.27
     acceptez
    -1.26
    fortawesome
    -1.26
     hijos
    -1.25
    POSITIVE LOGITS
     and
    2.09
    极了
    1.48
    ógicos
    1.38
    utique
    1.37
    )}}{
    1.33
     mūsų
    1.28
    niei
    1.28
    又は
    1.27
     if
    1.26
    paolo
    1.26
    Activations Density 0.009%

    No Known Activations