© 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. 10-GEMMASCOPE-RES-131K
    7. 9201
    Prev
    Next
    INDEX
    Explanations

    meeting someone

    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_10/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
    鲽
    -1.55
     платье
    -1.55
    妡
    -1.53
    meteries
    -1.48
     بدأ
    -1.44
     interesan
    -1.42
    vably
    -1.35
    痒
    -1.35
    $,
    -1.34
    萏
    -1.34
    POSITIVE LOGITS
     still
    1.37
    ⅼ
    1.35
     firmly
    1.34
     their
    1.31
     新聞
    1.29
    結果は
    1.25
     芋
    1.22
     on
    1.16
     out
    1.15
     led
    1.15
    Activations Density 0.018%

    No Known Activations