© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65200
    Prev
    Next
    INDEX
    Explanations

    synthesis of nanocrystals

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

    user names or identification codes in online comment sections or posts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron reliably fires on numeric tokens—especially digits and numbers used in dates, times, “days ago,” counts, and similar timestamp‐style contexts.

    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
     nase
    -1.14
     перец
    -1.14
     megane
    -1.12
    примеча
    -1.10
     Paroles
    -1.10
    יסטוריה
    -1.09
     Fils
    -1.09
     начин
    -1.09
    metido
    -1.08
    ֢
    -1.07
    POSITIVE LOGITS
     cárcel
    1.26
     финан
    1.23
     verdaderos
    1.20
    konstruktion
    1.20
     }}$,
    1.19
     delegación
    1.19
    ఱ
    1.18
     vorhandenen
    1.14
     berech
    1.13
    臜
    1.12
    Activations Density 0.002%

    No Known Activations