© 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. 9778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ******
    -0.98
     wiele
    -0.98
     anlat
    -0.98
     zeven
    -0.94
    MZ
    -0.94
     बहुत
    -0.94
     *******
    -0.92
    残酷
    -0.91
     or
    -0.90
    ları
    -0.89
    POSITIVE LOGITS
    ÈME
    1.08
    ал
    0.98
     Teilnehmer
    0.97
     alpes
    0.95
    ום
    0.94
     encontr
    0.94
     MÉ
    0.94
    Галерея
    0.94
    dopodob
    0.93
     investimento
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.