© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75562
    Prev
    Next
    INDEX
    Explanations

    before cessation

    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
    Than
    -1.28
    ter
    -1.25
     betrek
    -1.20
    melidir
    -1.20
    جاد
    -1.20
     more
    -1.20
    only
    -1.19
     pilihan
    -1.18
     without
    -1.16
     тільки
    -1.16
    POSITIVE LOGITS
     are
    1.20
     I
    1.16
     sen
    1.14
    }
    1.14
    まって
    1.11
     Examples
    1.11
     unterscheidet
    1.08
     “
    1.07
     returnValue
    1.07
    </sub>
    1.06
    Activations Density 0.031%

    No Known Activations