© 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. 70825
    Prev
    Next
    INDEX
    Explanations

    legal citation formats

    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
    Ѕ
    -1.13
     saisi
    -1.10
     kontin
    -1.03
     RÉ
    -1.01
    studentId
    -1.01
     черные
    -1.00
    *}$
    -1.00
     karbon
    -1.00
    #-
    -0.96
     smartphone
    -0.95
    POSITIVE LOGITS
     until
    1.08
     perché
    0.96
    istan
    0.93
     formação
    0.92
    
    0.91
     diámetro
    0.91
     Mauritania
    0.89
     equi
    0.88
    tillas
    0.88
     dreapta
    0.88
    Activations Density 0.001%

    No Known Activations