© 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. 41824
    Prev
    Next
    INDEX
    Explanations

    dating

    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
    了一眼
    -1.52
    vyš
    -1.45
     andra
    -1.44
    -¡
    -1.41
    nischen
    -1.38
    lierte
    -1.38
    ↳
    -1.33
     cercanos
    -1.32
     visar
    -1.30
     esposa
    -1.29
    POSITIVE LOGITS
    .
    1.60
     these
    1.52
     one
    1.39
     valorar
    1.39
    兩種
    1.37
    两种
    1.23
    馬上
    1.22
    These
    1.22
    也許
    1.22
     are
    1.21
    Activations Density 0.071%

    No Known Activations