© 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. 34-GEMMASCOPE-RES-131K
    7. 31561
    Prev
    Next
    INDEX
    Explanations

    evaluation metrics

    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
    Not in Any Lists

    No Comments

    Negative Logits
     verrou
    -1.03
    絝
    -1.00
     rembour
    -0.98
    諉
    -0.97
    Tory
    -0.94
    蝼
    -0.94
     sustancias
    -0.94
     étag
    -0.93
     silicona
    -0.92
     shir
    -0.91
    POSITIVE LOGITS
     of
    2.67
     achieved
    1.59
     for
    1.54
     with
    1.53
     when
    1.48
     in
    1.30
     achieve
    1.24
     achievable
    1.16
     after
    1.07
     offered
    1.05
    Activations Density 0.141%

    No Known Activations