© 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. 98497
    Prev
    Next
    INDEX
    Explanations

    function or method names

    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
     возможно
    -0.92
    actually
    -0.89
    Kapcsolódó
    -0.87
     studia
    -0.86
    UGU
    -0.85
     posled
    -0.85
     Lokasi
    -0.85
     zunächst
    -0.84
     نوشته
    -0.84
    Translation
    -0.84
    POSITIVE LOGITS
     this
    1.40
     other
    1.40
     but
    1.06
     only
    1.00
     another
    0.98
     doing
    0.95
    رأة
    0.92
     many
    0.92
     despite
    0.89
     abroad
    0.89
    Activations Density 0.064%

    No Known Activations