© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    conventional semiconductors, single hierarchy, surgery, techniques, either model, ground, these arguments, solely by, experimental measurements, Python

    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
     for
    -1.30
    
    -1.24
     about
    -1.22
     harap
    -1.16
     cœur
    -1.06
     questo
    -1.06
     with
    -1.05
    一会
    -1.05
     questa
    -1.05
    isinin
    -1.05
    POSITIVE LOGITS
     it
    1.29
     devido
    1.27
    sigma
    1.26
     hoặc
    1.25
     there
    1.20
    getNew
    1.17
     those
    1.17
    ↵↵↵
    1.15
    codigo
    1.14
     habituales
    1.12
    Activations Density 0.185%

    No Known Activations