© 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. 28057
    Prev
    Next
    INDEX
    Explanations

    code structure and testing

    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
    Istituto
    -1.08
    Università
    -1.07
     reafon
    -1.02
    mentes
    -0.89
     recent
    -0.88
     нат
    -0.86
     fhort
    -0.84
    fights
    -0.83
     nagu
    -0.82
    Accademia
    -0.82
    POSITIVE LOGITS
     test
    1.41
    test
    1.11
     товары
    1.04
     tests
    0.99
    roffen
    0.96
    등학교
    0.95
     variaciones
    0.94
    habitants
    0.94
     anfitrión
    0.93
     mempunyai
    0.92
    Activations Density 0.105%

    No Known Activations