© 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. 56849
    Prev
    Next
    INDEX
    Explanations

    conjunction connecting actions or states

    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
    anthe
    -1.02
    thof
    -0.99
     verzi
    -0.98
    糍
    -0.95
     indiví
    -0.94
     trám
    -0.94
    Setelah
    -0.93
    jiang
    -0.93
     sekä
    -0.90
    +#+#
    -0.90
    POSITIVE LOGITS
     with
    2.97
     without
    2.56
     in
    1.75
    without
    1.65
     at
    1.55
     on
    1.44
     без
    1.42
     under
    1.41
     within
    1.38
     Without
    1.38
    Activations Density 0.090%

    No Known Activations