© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114135
    Prev
    Next
    INDEX
    Explanations

    lawn care and maintenance

    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
    Negative Logits
    ?’
    -3.81
    ’)
    -3.20
     ”
    -3.16
    ’:
    -3.05
    !’
    -2.86
    ’;
    -2.81
    ↵
    -2.72
    瑧
    -2.61
    ”.
    -2.53
    !”
    -2.52
    POSITIVE LOGITS
     '
    3.56
    ↵↵
    3.09
    凩
    2.63
    ዡ
    2.41
    是很
    2.41
    >
    2.41
     essentials
    2.36
    -'
    2.34
    羮
    2.30
    仳
    2.28
    Activations Density 0.004%

    No Known Activations