© 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. 47995
    Prev
    Next
    INDEX
    Explanations

    code statements

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

    The neuron strongly responds to numeric literal tokens (e.g. “0”, “25”, 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_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
     if
    -1.98
    );
    -1.52
     wykonania
    -1.52
    屋の
    -1.45
     by
    -1.43
    两个
    -1.40
     a
    -1.38
    {
    -1.38
     the
    -1.37
     zrobić
    -1.33
    POSITIVE LOGITS
    </h3>
    2.00
    玧
    1.71
    This
    1.63
    膈
    1.45
     ทั้ง
    1.41
     réguli
    1.40
     ذلك
    1.40
    摁
    1.39
     dicha
    1.38
     This
    1.37
    Activations Density 0.004%

    No Known Activations