© 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. 34-GEMMASCOPE-RES-131K
    4. 80962
    Prev
    Next
    INDEX
    Explanations

    citations and years

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

    The neuron strongly activates on numeric tokens (especially multi‐digit numbers like years, citation IDs, section numbers, etc.).

    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
     then
    -1.05
     there
    -1.04
     instead
    -1.02
     zamiast
    -1.01
     when
    -1.00
     (
    -0.96
    それと
    -0.93
     should
    -0.88
    ハンドメイド
    -0.88
     вместо
    -0.86
    POSITIVE LOGITS
    readFileSync
    1.20
    styleable
    1.16
    styleType
    1.15
    伥
    1.13
    ccional
    1.13
    ();
    
    1.13
    @[+][
    1.12
     заказать
    1.11
    msgTypes
    1.10
     '.';
    1.10
    Activations Density 0.021%

    No Known Activations