© 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. 22-GEMMASCOPE-RES-131K
    7. 69167
    Prev
    Next
    INDEX
    Explanations

    boolean comparisons

    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_22/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
     در
    -0.85
    줄
    -0.84
     hoja
    -0.84
     而
    -0.82
    ksyon
    -0.81
    リーフ
    -0.80
    Filing
    -0.80
    ATHERINE
    -0.80
     уровня
    -0.79
     bundled
    -0.79
    POSITIVE LOGITS
    These
    0.94
    ➡
    0.91
     endwhile
    0.90
     reager
    0.88
    MDR
    0.88
    secta
    0.87
    ✳
    0.85
    푠
    0.85
    Each
    0.84
    listBox
    0.81
    Activations Density 0.027%

    No Known Activations