© 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. 81695
    Prev
    Next
    INDEX
    Explanations

    controller and class names

    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
    lateinit
    -0.78
    ционер
    -0.76
    tät
    -0.76
    ectos
    -0.76
    umbre
    -0.75
     build
    -0.75
     ഒ
    -0.73
    嚏
    -0.73
    tosh
    -0.72
     féminin
    -0.72
    POSITIVE LOGITS
     avaient
    0.85
     Aggarwal
    0.83
    otide
    0.83
    EVEN
    0.82
    drei
    0.81
     viewType
    0.79
     lotes
    0.77
    ГЛА
    0.77
     filozof
    0.77
    ]->
    0.77
    Activations Density 0.003%

    No Known Activations