© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7277
    Prev
    Next
    INDEX
    Explanations

    UI list widgets

    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
     Emphasis
    -1.02
     jahre
    -0.91
    なんだろう
    -0.88
    Emphasis
    -0.84
    を越
    -0.83
    mereka
    -0.82
    נח
    -0.79
    色が
    -0.79
    入って
    -0.78
     carattere
    -0.77
    POSITIVE LOGITS
     Príncipe
    0.93
    первых
    0.91
     compagnies
    0.91
    ícia
    0.90
     vinos
    0.88
     widget
    0.87
     SHOPPING
    0.87
    ⅱ
    0.86
    insics
    0.85
     köpa
    0.84
    Activations Density 0.065%

    No Known Activations