© 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. 40236
    Prev
    Next
    INDEX
    Explanations

    file paths and line numbers

    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
     three
    -1.68
    [
    -1.67
    v
    -1.67
    es
    -1.66
     what
    -1.60
    A
    -1.59
    其
    -1.58
     thinks
    -1.57
     innumerable
    -1.57
     widespread
    -1.55
    POSITIVE LOGITS
    ⑊
    1.66
    蓠
    1.59
    艄
    1.43
     interrump
    1.43
     splet
    1.41
                
    1.40
    ември
    1.40
     kral
    1.39
     diesem
    1.39
     dieser
    1.39
    Activations Density 0.001%

    No Known Activations