© 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. 19114
    Prev
    Next
    INDEX
    Explanations

    economic outlook and consumer demand

    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
    Sometimes
    -1.34
    Usually
    -1.25
    Many
    -1.23
    DESCRIPCIÓN
    -1.18
    It
    -1.17
    During
    -1.17
    พูด
    -1.16
    When
    -1.13
     OGSÅ
    -1.13
    Unlike
    -1.12
    POSITIVE LOGITS
     apesar
    1.45
     asegurarse
    1.27
     comienzan
    1.26
     forces
    1.23
     siguen
    1.20
    埴
    1.15
     botão
    1.13
     illustratie
    1.12
     adaptarse
    1.12
     inclui
    1.05
    Activations Density 0.064%

    No Known Activations