© 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. 59588
    Prev
    Next
    INDEX
    Explanations

    necessary actions for function

    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
     Déf
    -1.05
     anys
    -0.94
     използ
    -0.93
     мә
    -0.91
     tryna
    -0.90
     использования
    -0.89
     usati
    -0.89
    ⌵
    -0.87
    节省
    -0.87
    –¿
    -0.87
    POSITIVE LOGITS
     properly
    1.63
     successfully
    1.52
     get
    1.47
     ensure
    1.42
     successful
    1.39
    才能
    1.38
     succeed
    1.37
     make
    1.36
     complete
    1.32
     achieve
    1.26
    Activations Density 0.056%

    No Known Activations