© 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. 81731
    Prev
    Next
    INDEX
    Explanations

    vintage items and eras

    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
    abyte
    -0.95
    ワイン
    -0.91
    XC
    -0.91
    *****/
    -0.90
    キュリティ
    -0.90
    avadoc
    -0.89
    ***************/
    -0.89
     الفريق
    -0.89
    ַּ
    -0.88
     绒
    -0.88
    POSITIVE LOGITS
     vintage
    1.67
     circa
    1.32
    vintage
    1.29
     Depression
    1.16
    Depression
    1.08
    INTAGE
    1.05
    Vintage
    1.05
    Ephe
    1.05
     年代
    1.04
     Vintage
    1.03
    Activations Density 0.048%

    No Known Activations