© 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. 76130
    Prev
    Next
    INDEX
    Explanations

    take note or taking notice

    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
    öl
    -0.77
    Christi
    -0.76
    ហ
    -0.75
     Beruf
    -0.74
    andung
    -0.72
     Christi
    -0.70
     soldered
    -0.69
    zawa
    -0.69
    istet
    -0.69
     rú
    -0.68
    POSITIVE LOGITS
     notice
    2.53
     note
    2.41
    notice
    1.88
    note
    1.80
    Note
    1.72
    Notice
    1.71
     Notice
    1.65
    NOTICE
    1.56
     Note
    1.55
     NOTICE
    1.51
    Activations Density 0.038%

    No Known Activations