© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58832
    Prev
    Next
    INDEX
    Explanations

    existence of something

    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
     sommige
    -1.77
    翼翼
    -1.71
    ebenarnya
    -1.69
     ¤
    -1.61
    亖
    -1.60
     zeven
    -1.59
    臜
    -1.59
    簓
    -1.56
    乆
    -1.54
    ፑ
    -1.53
    POSITIVE LOGITS
     a
    1.93
     AND
    1.67
     occasional
    1.52
    𝟑
    1.52
     in
    1.45
    そのような
    1.41
     universo
    1.36
    関連リンク
    1.34
     no
    1.34
     obvious
    1.32
    Activations Density 0.021%

    No Known Activations