© 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. 34-GEMMASCOPE-RES-131K
    7. 77539
    Prev
    Next
    INDEX
    Explanations

    Ata-Zhurt party

    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_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
     flota
    -0.87
     escen
    -0.85
     industria
    -0.82
    があった
    -0.82
    を持っている
    -0.81
    refriger
    -0.81
     centru
    -0.81
     áreas
    -0.79
     cucina
    -0.78
    vibration
    -0.78
    POSITIVE LOGITS
     Similarly
    0.85
     damals
    0.81
    ココ
    0.75
     nemmeno
    0.75
    ©
    0.74
    GEN
    0.73
    к
    0.73
     επισ
    0.73
     lavori
    0.73
    as
    0.73
    Activations Density 0.002%

    No Known Activations