© 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. 84483
    Prev
    Next
    INDEX
    Explanations

    years in citations

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

    The neuron selectively activates on numeric tokens—particularly four‐digit numbers like publication years or reference identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ѝ
    -1.20
    日発売
    -1.16
    着脸
    -1.14
    📅
    -1.12
     Matéri
    -1.09
    见的
    -1.05
     valt
    -1.02
    stä
    -1.02
     букет
    -1.01
    zenden
    -1.01
    POSITIVE LOGITS
     anbieten
    1.15
     recently
    1.13
     kürzlich
    1.09
     недавно
    1.09
     lately
    1.06
     früheren
    1.03
     kolei
    1.02
     the
    1.02
    去看
    1.01
     our
    0.98
    Activations Density 0.019%

    No Known Activations