© 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. 60274
    Prev
    Next
    INDEX
    Explanations

    arithmetic sequences or formulas

    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
    These
    -1.23
    这些
    -1.18
     these
    -1.13
     such
    -1.04
     another
    -1.02
    Such
    -0.99
    這些
    -0.98
     этих
    -0.94
    Эти
    -0.92
     daarvan
    -0.88
    POSITIVE LOGITS
     expla
    0.87
     untill
    0.83
     expon
    0.81
    former
    0.81
    американ
    0.79
    直至
    0.79
     themselves
    0.77
     každého
    0.77
    ()])
    0.77
    pædia
    0.77
    Activations Density 0.019%

    No Known Activations