© 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. 22-GEMMASCOPE-RES-131K
    7. 15932
    Prev
    Next
    INDEX
    Explanations

    input shapes and assignments

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

    The neuron fires on numeric tokens and words indicating dimensional sizes or counts (e.g. numbers of inputs, layer nodes, array shapes).

    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
     प्रतिशत
    -1.13
     by
    -1.06
     mengalami
    -1.04
    ǥ
    -1.03
     actions
    -1.02
    ulico
    -1.02
     February
    -1.01
    маны
    -1.00
     this
    -0.98
    所说
    -0.98
    POSITIVE LOGITS
     širo
    1.13
     vaše
    1.04
     fréquent
    1.03
     Мед
    0.98
     hroz
    0.98
    Amar
    0.97
     saveurs
    0.95
     Стар
    0.94
     geniş
    0.93
     fueran
    0.93
    Activations Density 0.006%

    No Known Activations