© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74470
    Prev
    Next
    INDEX
    Explanations

    zinc finger DNA, Wireless bridging, NQF, Q:

    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
     even
    -2.45
     in
    -2.00
    Even
    -1.95
    Some
    -1.92
     at
    -1.90
     just
    -1.80
    );
    -1.74
     Two
    -1.73
    !!!!!
    -1.71
     often
    -1.70
    POSITIVE LOGITS
    ſſen
    1.73
     famed
    1.70
    ఽ
    1.64
     étages
    1.63
     thc
    1.63
     ziemi
    1.62
     czter
    1.61
    ፨
    1.61
     Dinas
    1.60
     horrid
    1.59
    Activations Density 0.000%

    No Known Activations