© 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. 10-GEMMASCOPE-RES-131K
    4. 110516
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    the asterisk symbol (*) in code, typically used for pointers, multiplication, or wildcards.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron specializes in spotting the asterisk “*” token, as used to denote pointers or multiplication operators in code.

    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
     этом
    -1.64
     quoique
    -1.63
     same
    -1.55
     brazen
    -1.52
     about
    -1.50
     berech
    -1.49
    が見えて
    -1.45
     делает
    -1.43
     castelo
    -1.41
     fosters
    -1.40
    POSITIVE LOGITS
    års
    1.59
    蛧
    1.52
    ytale
    1.40
    sukienka
    1.40
     bekym
    1.39
    kosten
    1.34
    ในการ
    1.34
    žel
    1.34
    '';
    1.34
    FundMe
    1.33
    Activations Density 0.004%

    No Known Activations