© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128816
    Prev
    Next
    INDEX
    Explanations

    user selects and returns values

    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
     permanentes
    -0.94
    homePage
    -0.91
    moderne
    -0.91
    när
    -0.91
     Elektron
    -0.90
    elezo
    -0.90
    ischem
    -0.89
    Halaman
    -0.88
    Summon
    -0.88
     ansvar
    -0.88
    POSITIVE LOGITS
    getSelected
    1.08
    getUser
    1.02
    Returned
    0.95
     returned
    0.95
     return
    0.95
     result
    0.94
     선택
    0.92
    Return
    0.90
     после
    0.90
    user
    0.87
    Activations Density 0.006%

    No Known Activations