© 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. 22-GEMMASCOPE-RES-131K
    4. 36687
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
     γνω
    -0.85
    вня
    -0.85
    lexia
    -0.77
    МЕ
    -0.76
    ilera
    -0.74
     veľa
    -0.74
    lorus
    -0.73
    jaan
    -0.73
     Later
    -0.73
    中式
    -0.73
    POSITIVE LOGITS
    *)&
    0.94
    fordshire
    0.88
     escen
    0.88
     TextInputType
    0.87
     entreprise
    0.85
    mighty
    0.84
     Trainer
    0.84
    ramientas
    0.84
     eixo
    0.83
     granos
    0.82
    Activations Density 0.067%

    No Known Activations