© 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. 82649
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    propTypes
    -0.77
     καὶ
    -0.74
    ómicas
    -0.71
     elegans
    -0.71
     Chairs
    -0.71
     RV
    -0.71
    Տ
    -0.71
    SiO
    -0.70
    Jb
    -0.70
    Править
    -0.69
    POSITIVE LOGITS
    acjach
    0.78
    ждение
    0.74
    年間
    0.73
    itzenden
    0.73
    ínguez
    0.72
     something
    0.72
    underbrace
    0.72
    rungsseite
    0.71
    ᕙ
    0.68
     yet
    0.67
    Activations Density 0.008%

    No Known Activations