© 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. 83822
    Prev
    Next
    INDEX
    Explanations

    technical code and data fragments

    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
    <bos>
    -0.91
    があります
    -0.87
    oires
    -0.83
     besonderen
    -0.81
    clusal
    -0.80
     cosas
    -0.80
    strual
    -0.79
     обмен
    -0.79
    <0xA3>
    -0.78
    ünstler
    -0.77
    POSITIVE LOGITS
     massive
    1.05
     vast
    1.02
     great
    1.01
     beautiful
    0.94
    ombre
    0.93
     huge
    0.92
     plus
    0.92
    Plus
    0.92
    トヨタ
    0.89
     large
    0.88
    Activations Density 0.002%

    No Known Activations