© 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. 10-GEMMASCOPE-RES-131K
    7. 60097
    Prev
    Next
    INDEX
    Explanations

    fall of something

    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
    Достоинства
    -2.22
    ୈ
    -2.03
    are
    -1.98
    汩
    -1.94
     彈
    -1.91
    from
    -1.91
    During
    -1.89
    錞
    -1.88
    
    -1.88
    se
    -1.83
    POSITIVE LOGITS
    🦣
    1.88
     podrían
    1.87
     into
    1.79
    ᯾
    1.77
    नलोड
    1.77
     encontrada
    1.76
     quedan
    1.73
    雱
    1.73
     così
    1.73
    ༷
    1.73
    Activations Density 0.026%

    No Known Activations