© 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. 34-GEMMASCOPE-RES-131K
    7. 34701
    Prev
    Next
    INDEX
    Explanations

    multilingual section labels

    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_34/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
    There
    -1.70
     There
    -1.40
     when
    -1.32
     When
    -1.32
     Because
    -1.30
    When
    -1.30
     before
    -1.25
    because
    -1.24
     two
    -1.24
     Since
    -1.23
    POSITIVE LOGITS
     lópez
    1.36
     défauts
    1.30
     manifestó
    1.30
     compresión
    1.28
     trám
    1.27
     garcía
    1.25
     clínicos
    1.23
    @[+][
    1.21
     responsabilità
    1.20
     exercícios
    1.20
    Activations Density 0.003%

    No Known Activations