© 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. 119625
    Prev
    Next
    INDEX
    Explanations

    presents

    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
    2
    -3.78
    6
    -2.47
    8
    -2.34
    3
    -2.33
    _{
    -2.31
    7
    -2.27
    5
    -2.11
    in
    -2.06
                
    -1.95
    4
    -1.92
    POSITIVE LOGITS
     plásticos
    2.11
     armado
    2.06
     residuos
    2.06
     tratados
    2.03
     escritos
    2.03
     exclusivo
    2.02
     rocas
    2.00
    貍
    2.00
     salarios
    2.00
     compradores
    1.99
    Activations Density 0.034%

    No Known Activations