© 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. 33511
    Prev
    Next
    INDEX
    Explanations

    php code

    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
    ,*
    -0.82
     ihren
    -0.74
     fragen
    -0.73
    orton
    -0.70
     peur
    -0.67
    сыпа
    -0.66
     bekam
    -0.66
     Хи
    -0.66
     玫瑰
    -0.65
    pants
    -0.65
    POSITIVE LOGITS
     esc
    0.81
     echo
    0.78
    INES
    0.73
    printf
    0.73
    bilities
    0.73
    ném
    0.72
    issima
    0.72
     hah
    0.71
    ksz
    0.71
     printf
    0.71
    Activations Density 0.005%

    No Known Activations