© 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. 3493
    Prev
    Next
    INDEX
    Explanations

    preparation and placement

    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
    undu
    -0.94
    Certain
    -0.90
    many
    -0.87
     Certain
    -0.87
     bloß
    -0.84
     certain
    -0.83
    berian
    -0.83
    CRR
    -0.81
    nexpected
    -0.81
     nying
    -0.81
    POSITIVE LOGITS
     your
    1.59
     prepared
    1.48
     подготов
    1.16
     a
    1.13
    prepared
    1.12
     allerede
    1.04
     Prepared
    1.03
     heated
    1.03
    Prepared
    1.00
    已经
    0.98
    Activations Density 0.034%

    No Known Activations