© 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. 22-GEMMASCOPE-RES-131K
    4. 53960
    Prev
    Next
    INDEX
    Explanations

    data type specifications

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

    The neuron fires on programming keywords that name or specify types (e.g. dataType, responseType, filetype).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    罴
    -1.34
     mismas
    -1.29
    窳
    -1.28
    ѣмъ
    -1.26
    泺
    -1.26
     famosos
    -1.25
     élevée
    -1.24
     permanentes
    -1.23
     graciosas
    -1.22
    蓍
    -1.20
    POSITIVE LOGITS
    '
    1.30
    олові
    1.27
    {
    1.23
    <bos>
    1.20
    ínas
    1.19
     Handlungen
    1.10
    
    1.09
    ();)
    1.09
     vollständige
    1.09
    Both
    1.09
    Activations Density 0.001%

    No Known Activations