© 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. 34-GEMMASCOPE-RES-131K
    7. 98836
    Prev
    Next
    INDEX
    Explanations

    cell adhesion molecule

    np_acts-logits-general · gemini-2.5-flash-lite

    XML/code markup in technical documents, particularly Android-related syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Наталья
    -0.88
    ムラ
    -0.83
    Kini
    -0.79
    缓慢
    -0.79
     LEO
    -0.77
    芸能
    -0.76
     Waco
    -0.75
     animación
    -0.75
    zené
    -0.75
     岛
    -0.74
    POSITIVE LOGITS
    ческие
    0.83
    jø
    0.81
     pelvic
    0.77
     empathy
    0.75
    Ų
    0.73
    PRODU
    0.73
    ;++
    0.73
     возду
    0.72
    ското
    0.72
    CRM
    0.71
    Activations Density 0.000%

    No Known Activations