© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71368
    Prev
    Next
    INDEX
    Explanations

    code `if/else` blocks

    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
     что
    -0.82
     patria
    -0.82
    ✦
    -0.81
     acknowledges
    -0.79
    EXHIB
    -0.78
     Eigenschaften
    -0.77
     Только
    -0.77
    getSimpleName
    -0.76
    这样的
    -0.76
     Ген
    -0.76
    POSITIVE LOGITS
     menny
    1.05
    PARTMENT
    0.97
     eikä
    0.96
     sandalias
    0.94
    缺少
    0.90
    heen
    0.89
     onderdelen
    0.89
    わりに
    0.88
     continuing
    0.88
     ندار
    0.88
    Activations Density 0.002%

    No Known Activations