© 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. 15040
    Prev
    Next
    INDEX
    Explanations

    second, secondly

    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
    badan
    -1.97
     første
    -1.95
    tividade
    -1.87
     leiding
    -1.74
     allzu
    -1.70
    vermectin
    -1.70
    zzet
    -1.62
     forbindelse
    -1.61
     början
    -1.59
    pearance
    -1.58
    POSITIVE LOGITS
     we
    1.70
     notor
    1.66
     why
    1.54
    似乎
    1.53
     indispens
    1.48
     implacable
    1.42
     importantly
    1.42
     everything
    1.41
     you
    1.41
     تعدى
    1.40
    Activations Density 0.020%

    No Known Activations