© 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. 45433
    Prev
    Next
    INDEX
    Explanations

    Papua New Guinea, Influence, Control

    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
    Not in Any Lists

    No Comments

    Negative Logits
    """
    -2.23
    ();
    -1.91
    <i>
    -1.91
    \
    -1.91
     our
    -1.88
    </h3>
    -1.88
    E
    -1.76
    from
    -1.75
    ll
    -1.70
    (\
    -1.70
    POSITIVE LOGITS
     začet
    1.78
    俟
    1.74
    伫
    1.71
     kjer
    1.67
    翳
    1.65
    揩
    1.65
     podjet
    1.63
    peinture
    1.62
       
    1.55
     glede
    1.55
    Activations Density 0.006%

    No Known Activations