© 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. 20735
    Prev
    Next
    INDEX
    Explanations

    Columbus Day, Columbus Nova, Columbus Crew

    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
     gelas
    -2.91
     risiko
    -2.52
    没
    -2.45
     kaca
    -2.41
    1
    -2.38
    疴
    -2.31
    变成了
    -2.27
     praktisch
    -2.27
     sarung
    -2.20
    两
    -2.20
    POSITIVE LOGITS
    this
    3.17
    蘼
    2.77
    饹
    2.52
    闥
    2.47
     ähnliche
    2.45
     Betrach
    2.36
    蟻
    2.36
    事了
    2.36
    鱻
    2.33
    ’,
    2.28
    Activations Density 0.016%

    No Known Activations