© 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. 83916
    Prev
    Next
    INDEX
    Explanations

    sequence patterns

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical notation and sequence patterns, particularly in number theory problems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Eylül
    -0.77
     короб
    -0.75
     wsp
    -0.75
     augusti
    -0.74
    企画
    -0.73
     Aralık
    -0.73
    herz
    -0.72
    ％
    -0.72
     Terbaik
    -0.71
     Grö
    -0.71
    POSITIVE LOGITS
     OE
    1.44
    OE
    1.30
     sequence
    1.13
     oe
    0.97
    sequence
    0.93
     Sloane
    0.86
    ""}
    0.84
    Sequence
    0.84
     Sequence
    0.83
     オンライン
    0.83
    Activations Density 0.059%

    No Known Activations