© 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. 11288
    Prev
    Next
    INDEX
    Explanations

    R documentation: \name, \alias, \title

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

    R programming language code and documentation syntax.

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

    The neuron activates on fragments of R error messages (e.g. “Error in … cannot coerce type ‘character’ to vector of type …”).

    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
    ✇
    -1.43
    NewUrl
    -1.41
     玄関
    -1.38
     новая
    -1.35
     蒸
    -1.35
    utri
    -1.35
     emblematic
    -1.34
    粢
    -1.34
    ｓ
    -1.34
     alleging
    -1.33
    POSITIVE LOGITS
     you
    1.48
     However
    1.34
    räck
    1.30
     Two
    1.30
    displaystyle
    1.27
     As
    1.26
    『
    1.24
     when
    1.23
    来
    1.23
     Since
    1.23
    Activations Density 0.103%

    No Known Activations