© 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. 10-GEMMASCOPE-RES-131K
    7. 74969
    Prev
    Next
    INDEX
    Explanations

    his or her family member

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

    The neuron fires on numeric tokens—years, ages, counts, statistics, or any numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    );
    -1.57
     them
    -1.48
     голове
    -1.41
     sono
    -1.31
    硨
    -1.24
    quelize
    -1.23
    食べた
    -1.23
    niejs
    -1.20
    دهم
    -1.20
     necesitaba
    -1.16
    POSITIVE LOGITS
     parlare
    1.42
    šené
    1.38
     jardines
    1.36
    那里
    1.36
     Truly
    1.29
    there
    1.29
    NEN
    1.28
    柠
    1.27
     other
    1.27
     geweldig
    1.26
    Activations Density 0.006%

    No Known Activations