© 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. 118569
    Prev
    Next
    INDEX
    Explanations

    code imports and file paths

    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
    碓
    -0.90
    );
    -0.80
    狂
    -0.79
    zioso
    -0.78
     GUR
    -0.77
     Bugs
    -0.76
    👞
    -0.76
    ؟؟
    -0.75
     gris
    -0.74
     listing
    -0.74
    POSITIVE LOGITS
    Familie
    0.84
    それ
    0.83
    дель
    0.82
    štění
    0.82
     ў
    0.82
     chọn
    0.81
    öscht
    0.80
     উ
    0.80
    เ
    0.79
    urni
    0.79
    Activations Density 1.834%

    No Known Activations