© 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. 98579
    Prev
    Next
    INDEX
    Explanations

    starts of specific phrases

    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
    怎麼
    -0.81
     人民
    -0.79
     perten
    -0.79
     policia
    -0.78
     storey
    -0.75
     DPRD
    -0.75
     twelve
    -0.74
    UARY
    -0.74
     operar
    -0.74
    Having
    -0.73
    POSITIVE LOGITS
    ifor
    0.81
     BJ
    0.79
    âm
    0.77
    IFORM
    0.77
    BJ
    0.77
    гли
    0.77
    記録
    0.74
    owane
    0.73
     山田
    0.72
     Ressourcen
    0.72
    Activations Density 0.000%

    No Known Activations