© 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. 39804
    Prev
    Next
    INDEX
    Explanations

    stable followed by a noun

    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
     hefty
    -3.14
    撄
    -3.11
     unbelievably
    -2.98
     revered
    -2.95
     .......
    -2.94
     wacky
    -2.91
     drenched
    -2.91
     ........
    -2.88
     quintessential
    -2.88
     spectacular
    -2.86
    POSITIVE LOGITS
    With
    3.73
    i
    3.67
    Shortly
    3.41
    Despite
    3.28
    Perhaps
    3.27
    Ironically
    3.19
    Regardless
    3.16
     With
    3.16
     exquisitely
    3.16
     unwavering
    3.14
    Activations Density 0.006%

    No Known Activations