© 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. 34-GEMMASCOPE-RES-131K
    7. 76741
    Prev
    Next
    INDEX
    Explanations

    quoted strings or assignments

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

    The neuron fires on numeric literals (and the surrounding comparison/assignment punctuation), i.e. tokens representing numbers or number‐related operators.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Initially
    -0.89
    Initially
    -0.86
    utente
    -0.85
    With
    -0.85
    仕方ない
    -0.83
    eled
    -0.82
     initially
    -0.81
    出る
    -0.81
    わけではない
    -0.80
    いっ
    -0.80
    POSITIVE LOGITS
     "
    1.90
     “
    1.85
     '
    1.25
    「
    1.21
    =>'
    1.17
     MemoryStream
    1.15
    <<"
    1.14
    ="
    1.14
     ‘
    1.12
    '=>'
    1.08
    Activations Density 0.062%

    No Known Activations