© 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. 22-GEMMASCOPE-RES-131K
    7. 13827
    Prev
    Next
    INDEX
    Explanations

    booked, relation, access, assessment, python

    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_22/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
    技術
    -0.96
     AGAIN
    -0.83
    abilities
    -0.82
    кту
    -0.80
    óp
    -0.79
    jskiej
    -0.79
    עים
    -0.78
     alcal
    -0.76
     GoFundMe
    -0.76
    ידה
    -0.76
    POSITIVE LOGITS
     に関する
    0.87
     actual
    0.83
     real
    0.81
     autén
    0.81
    おめでとう
    0.80
    cookieParser
    0.80
    icef
    0.78
    應該
    0.77
    bản
    0.77
    Характеристики
    0.76
    Activations Density 0.192%

    No Known Activations