© 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. 67460
    Prev
    Next
    INDEX
    Explanations

    card, article, com, development, 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
     unbelievably
    -1.84
    
    -1.80
     exceptionally
    -1.75
     realmente
    -1.72
    泚
    -1.72
     取り付け
    -1.63
    stücks
    -1.62
     REALLY
    -1.61
     vraiment
    -1.60
    一下子
    -1.59
    POSITIVE LOGITS
     возникает
    1.77
     comprometido
    1.77
    傩
    1.76
    From
    1.74
     two
    1.74
     provide
    1.69
    ⬮
    1.69
     encantado
    1.68
     diminish
    1.68
     newly
    1.68
    Activations Density 0.001%

    No Known Activations