© 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. 98406
    Prev
    Next
    INDEX
    Explanations

    mathematical equation solutions

    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
     anderen
    -1.10
     verden
    -1.02
     andere
    -1.00
     internes
    -0.89
     noticias
    -0.85
    topRight
    -0.84
     outros
    -0.83
    andere
    -0.82
    endfor
    -0.81
    めに
    -0.81
    POSITIVE LOGITS
     uiteindelijk
    0.96
     finally
    0.90
     Finalmente
    0.89
    ))$.
    0.85
     Umständen
    0.85
    цезда
    0.85
    alui
    0.83
     ultimately
    0.83
     Wiktionnaire
    0.82
    icus
    0.82
    Activations Density 0.048%

    No Known Activations