© 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. 15584
    Prev
    Next
    INDEX
    Explanations

    chance that

    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
     from
    -2.22
    ?”
    -1.86
     on
    -1.69
     Such
    -1.61
     to
    -1.59
    .”
    -1.48
     عمان
    -1.48
     and
    -1.43
    ].
    -1.41
     methods
    -1.38
    POSITIVE LOGITS
     you
    2.41
     trône
    1.77
     régal
    1.60
     istrinya
    1.55
    {
    1.52
    见状
    1.48
    お風呂
    1.46
    ཋ
    1.45
    让你
    1.45
    很赞
    1.40
    Activations Density 0.009%

    No Known Activations