© 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. 10-GEMMASCOPE-RES-131K
    7. 123664
    Prev
    Next
    INDEX
    Explanations

    of and prepositional phrases

    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_10/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
     of
    -2.39
    d
    -2.20
    </h2>
    -2.17
    
    -2.09
    ")]
    -1.97
    ']
    -1.96
     ")
    -1.92
    >
    -1.91
    檍
    -1.91
     yogur
    -1.90
    POSITIVE LOGITS
    _
    3.19
    ’
    2.97
    >
    2.31
    秾
    2.23
    )
    2.16
     Перейти
    2.16
     you
    2.09
    糴
    2.09
     funktionieren
    2.08
     reconocidos
    2.08
    Activations Density 0.107%

    No Known Activations