© 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. 68553
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    Because
    -2.14
    mathrm
    -2.13
     because
    -2.03
    because
    -1.85
    Generally
    -1.80
    Also
    -1.79
    既に
    -1.77
    Unlike
    -1.77
    While
    -1.73
     that
    -1.72
    POSITIVE LOGITS
    僦
    1.81
     dió
    1.63
    鈊
    1.63
     blatant
    1.59
     myriad
    1.50
    "
    1.49
     \&
    1.49
     patrulla
    1.41
    の意味
    1.38
    这次
    1.37
    Activations Density 0.005%

    No Known Activations