© 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. 58381
    Prev
    Next
    INDEX
    Explanations

    anyhow, way, how, enhancer, xref

    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
     
    -3.03
    A
    -2.83
    the
    -2.75
     idyllic
    -2.64
    ti
    -2.63
    T
    -2.58
    {
    -2.53
     (
    -2.44
     Truly
    -2.34
    ↵
    -2.33
    POSITIVE LOGITS
    錞
    3.17
    msgTypes
    2.75
    ﮑ
    2.69
    wahati
    2.64
     JAKARTA
    2.59
    ጹ
    2.56
    桄
    2.50
    倂
    2.50
    屙
    2.45
    CodeAttribute
    2.42
    Activations Density 0.002%

    No Known Activations