© 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. 1799
    Prev
    Next
    INDEX
    Explanations

    list of allowed values

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

    The neuron activates on lines in code‐related text that list or enumerate “allowed” or “possible” values (e.g. parameter/value specifications and their colons).

    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
     måste
    -1.27
    駐車
    -1.26
    rangian
    -1.23
     valueOf
    -1.20
         
    -1.20
    taya
    -1.17
     sehr
    -1.16
    ʆ
    -1.16
    صة
    -1.16
    woners
    -1.16
    POSITIVE LOGITS
    D
    1.48
    S
    1.45
    C
    1.44
    들을
    1.38
    ERÍA
    1.34
    多种
    1.32
     verschied
    1.31
    including
    1.30
     ladite
    1.30
    by
    1.29
    Activations Density 0.020%

    No Known Activations