© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    standard library imports

    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
    ådet
    -1.29
    gantung
    -1.28
    maillot
    -1.09
     this
    -1.05
    firmasi
    -1.04
     wichtige
    -1.04
     Erkrankungen
    -1.04
     Erkrank
    -1.01
    ượu
    -1.00
     when
    -0.97
    POSITIVE LOGITS
    begin
    1.02
    two
    0.99
    cons
    0.87
     glau
    0.87
     HomeComponent
    0.85
     двух
    0.84
     dziew
    0.82
     возвра
    0.82
    Parametros
    0.81
     них
    0.81
    Activations Density 0.092%

    No Known Activations