© 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. 33206
    Prev
    Next
    INDEX
    Explanations

    Source information and technical details

    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
     Архів
    -0.96
     condol
    -0.77
     castello
    -0.75
    耨
    -0.73
    cosmos
    -0.73
     xk
    -0.73
    ESSO
    -0.72
    เช่น
    -0.71
    쌓
    -0.70
    묶
    -0.69
    POSITIVE LOGITS
    <code>
    1.63
     cite
    0.85
     line
    0.83
    Parametro
    0.82
     MacKenzie
    0.81
     Unknown
    0.78
     parameter
    0.78
     Parameter
    0.78
     More
    0.77
    More
    0.76
    Activations Density 0.018%

    No Known Activations