© 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. 66641
    Prev
    Next
    INDEX
    Explanations

    reducing costs or commissions

    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
     vyp
    -0.79
     oraciones
    -0.79
    mmas
    -0.75
    bleven
    -0.74
    重視
    -0.72
     niño
    -0.72
     iż
    -0.71
     commerciales
    -0.70
     perdagangan
    -0.69
    resumen
    -0.69
    POSITIVE LOGITS
     paroi
    0.90
    ']>;
    0.90
     stras
    0.86
    Ꮳ
    0.82
     velg
    0.82
    rictions
    0.82
     juan
    0.79
    로드
    0.78
     ...............
    0.77
     Herv
    0.76
    Activations Density 0.058%

    No Known Activations