© 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. 34-GEMMASCOPE-RES-131K
    7. 62474
    Prev
    Next
    INDEX
    Explanations

    closing html tags

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     the
    -1.10
     in
    -1.09
     so
    -0.99
     vuonna
    -0.93
     from
    -0.92
     Also
    -0.91
     spannende
    -0.90
     shouldBe
    -0.90
    Also
    -0.89
     Being
    -0.87
    POSITIVE LOGITS
    ">
    1.75
    '>
    1.37
    \">
    1.17
     latter
    1.12
    ">
    1.11
    ;">
    1.09
     demokra
    1.08
     seksi
    1.07
     INGREDIENTS
    1.04
     vermelho
    1.00
    Activations Density 0.012%

    No Known Activations