© 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. 54400
    Prev
    Next
    INDEX
    Explanations

    import statements and domain/model definitions

    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
     Administración
    -1.16
    leine
    -1.15
    tasse
    -1.09
    ieR
    -1.09
    iaomi
    -1.09
     berasal
    -1.04
    ⊄
    -1.02
    libra
    -1.01
     dirait
    -0.98
     简介
    -0.98
    POSITIVE LOGITS
    Здра
    1.09
    Комплек
    1.05
    ch
    1.02
    _
    1.00
    uck
    0.99
    key
    0.93
    Дет
    0.91
    Прода
    0.90
    mu
    0.90
    er
    0.88
    Activations Density 0.002%

    No Known Activations