© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    lists that are

    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
    aziland
    -0.97
    dialement
    -0.96
    cego
    -0.96
    idue
    -0.95
    Aç
    -0.92
    पि
    -0.91
    sklä
    -0.89
    larım
    -0.88
    íc
    -0.88
     malzeme
    -0.87
    POSITIVE LOGITS
     are
    3.27
     is
    1.98
    分别是
    1.63
     são
    1.55
     हैं
    1.54
     είναι
    1.48
    :
    1.41
     jsou
    1.33
     следующие
    1.30
     follows
    1.30
    Activations Density 0.116%

    No Known Activations