© 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. 73458
    Prev
    Next
    INDEX
    Explanations

    directed against or toward

    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
    ในการ
    -0.81
    xelles
    -0.78
    ysio
    -0.76
     股份
    -0.74
    vaig
    -0.73
    韋
    -0.73
    Willing
    -0.71
    inspire
    -0.70
    提供了
    -0.70
    处理
    -0.69
    POSITIVE LOGITS
     directed
    5.38
    directed
    4.38
     Directed
    3.97
    Directed
    3.89
     aimed
    3.83
     targeting
    3.42
     targeted
    3.33
     направ
    3.27
     dirigido
    2.92
     dirigida
    2.86
    Activations Density 0.228%

    No Known Activations