© 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. 70915
    Prev
    Next
    INDEX
    Explanations

    URL parameters and identifiers

    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
     somewhat
    -1.50
     vii
    -1.46
     yaka
    -1.43
     terrific
    -1.40
     decidedly
    -1.34
     foton
    -1.33
     eko
    -1.33
    鷽
    -1.31
     ridiculous
    -1.29
     VERY
    -1.29
    POSITIVE LOGITS
     helps
    1.44
     gets
    1.42
     allows
    1.41
     get
    1.40
     bring
    1.39
    Being
    1.36
     facilitates
    1.35
     enables
    1.31
     Particularly
    1.30
     take
    1.29
    Activations Density 0.006%

    No Known Activations