© 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. 118884
    Prev
    Next
    INDEX
    Explanations

    belongs to

    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
     okazji
    -2.28
    
    -2.28
    вгений
    -2.13
     adhesivo
    -2.13
     colheres
    -2.02
    ſem
    -1.99
    vább
    -1.98
    llten
    -1.98
     wußte
    -1.96
    웻
    -1.95
    POSITIVE LOGITS
     For
    2.73
     Then
    2.28
    </b>
    2.22
     There
    2.22
     Except
    2.16
     They
    2.16
     you
    2.13
     With
    2.11
     From
    2.06
     Also
    2.06
    Activations Density 0.008%

    No Known Activations