© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99399
    Prev
    Next
    INDEX
    Explanations

    counterpart, partner, peer

    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
    .
    -2.14
    </em>
    -1.99
     ”
    -1.88
    ）：
    -1.81
    ”
    -1.77
     gesamte
    -1.70
    !”
    -1.65
     You
    -1.53
     bellissimo
    -1.53
    ?”
    -1.52
    POSITIVE LOGITS
    
    2.03
    ien
    1.80
    𖥧
    1.79
    ea
    1.73
     inspirasi
    1.69
    al
    1.63
    おわりに
    1.63
    ia
    1.62
    鯔
    1.62
    om
    1.59
    Activations Density 0.010%

    No Known Activations