© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70400
    Prev
    Next
    INDEX
    Explanations

    years and film titles

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

    The neuron strongly activates on four-digit numerals that denote years (especially years in parentheses following film titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    のでしょうか
    -1.24
     they
    -1.20
    のでしょう
    -1.18
    のですね
    -1.16
    のではないでしょうか
    -1.13
    を越
    -1.09
    )−
    -1.09
    });*/
    -1.07
     Instyt
    -1.07
     kecamatan
    -1.05
    POSITIVE LOGITS
    そして
    1.27
    لباس
    1.27
    ถ้า
    1.27
    しかし
    1.26
    Honduras
    1.18
    Når
    1.15
    然而
    1.15
    Setelah
    1.13
    ร้าน
    1.13
    <bos>
    1.13
    Activations Density 0.023%

    No Known Activations