© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112241
    Prev
    Next
    INDEX
    Explanations

    error codes fields

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

    hexadecimal error codes or numeric identifiers in technical documentation.

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

    The neuron fires on code‐style identifiers and labels—especially uppercase names or tokens used as keys or section headings.

    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
    y
    -1.63
     by
    -1.63
     for
    -1.60
     my
    -1.55
     our
    -1.50
     chose
    -1.45
    相同的
    -1.45
     should
    -1.44
     it
    -1.43
     gave
    -1.40
    POSITIVE LOGITS
     mondi
    1.63
    ৢ
    1.56
     этих
    1.50
    olge
    1.45
    signable
    1.45
     étr
    1.43
     ,'
    1.41
    省市镇
    1.41
    ever
    1.39
    these
    1.39
    Activations Density 0.002%

    No Known Activations