© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26578
    Prev
    Next
    INDEX
    Explanations

    images, graphics, context

    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
    (\%)
    -0.90
    itives
    -0.84
    benzene
    -0.83
    SuccessListener
    -0.82
     still
    -0.82
    '>
    -0.81
    比亚
    -0.78
     känns
    -0.77
    ран
    -0.77
     xvii
    -0.77
    POSITIVE LOGITS
    벵
    0.90
     atendimento
    0.84
    ступљено
    0.83
    Kiri
    0.83
    以上です
    0.81
     criti
    0.81
    recen
    0.79
     見え
    0.79
    immig
    0.77
     critici
    0.76
    Activations Density 0.017%

    No Known Activations