© 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. 103629
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and geographical terms

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

    words or tokens related to programming concepts, particularly those involving relationships, data types, or technical terms in code and documentation.

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

    The neuron spikes on individual domain-specific or proper-name tokens (e.g. library headers, software/framework names, place or organization names).

    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
    诓
    -2.75
    zembro
    -2.69
    tku
    -2.63
     dass
    -2.63
    椟
    -2.61
    迓
    -2.55
    宠物
    -2.50
    zja
    -2.45
    ᨕ
    -2.45
    chtenstein
    -2.44
    POSITIVE LOGITS
    They
    3.00
    他
    2.66
    ()
    2.66
    There
    2.64
    >
    2.61
    D
    2.59
    You
    2.58
    ра
    2.53
    i
    2.53
    //
    2.47
    Activations Density 0.001%

    No Known Activations