© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127683
    Prev
    Next
    INDEX
    Explanations

    ref- followed by other morphemes

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

    The neuron activates on occurrences of “ref” reference markers (i.e. citation tags).

    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
    and
    -2.80
     utilizan
    -2.50
    ↵↵
    -2.34
    ology
    -2.28
    or
    -2.22
     男人
    -2.20
     are
    -2.20
     possam
    -2.09
    房屋
    -2.02
    et
    -2.00
    POSITIVE LOGITS
    彼女の
    2.75
    洐
    2.69
    鈇
    2.66
    d
    2.63
    妺
    2.38
    
    2.38
    橚
    2.38
     για
    2.36
    鱚
    2.31
    Ⲉ
    2.30
    Activations Density 0.002%

    No Known Activations