© 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. 76682
    Prev
    Next
    INDEX
    Explanations

    Objective-C import statements

    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
    łącz
    -0.85
     aus
    -0.81
    孵
    -0.79
     includes
    -0.76
     çok
    -0.75
    ետ
    -0.73
     sw
    -0.72
     little
    -0.72
    ält
    -0.72
     dari
    -0.72
    POSITIVE LOGITS
    import
    1.07
     importing
    1.00
     import
    0.98
     importation
    0.95
     Importing
    0.91
     IMPORT
    0.84
     Import
    0.82
     imports
    0.78
     elér
    0.77
    מונה
    0.76
    Activations Density 0.021%

    No Known Activations