© 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. 47236
    Prev
    Next
    INDEX
    Explanations

    upon which

    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
     praktijk
    -0.75
    CCIÓN
    -0.73
    peel
    -0.73
    bros
    -0.72
     recém
    -0.72
    😒
    -0.72
    ',)
    -0.71
    &,
    -0.71
    kate
    -0.71
    🗿
    -0.70
    POSITIVE LOGITS
    </sup>
    0.96
    </
    0.82
    </h2>
    0.79
    而
    0.76
    </b>
    0.75
    </h6>
    0.74
    하였다
    0.74
    ocrine
    0.73
    </strong>
    0.72
     Kurds
    0.72
    Activations Density 0.007%

    No Known Activations