© 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. 32350
    Prev
    Next
    INDEX
    Explanations

    compute tomography

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

    The neuron fires on occurrences of the “comput” root (e.g. tokens like “Computed,” “computed,” or “compute”).

    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
     刺繍
    -1.14
     continuare
    -1.13
    出てきた
    -1.02
     consentimiento
    -0.99
     Vgl
    -0.97
     continúas
    -0.96
     محور
    -0.95
    pantalón
    -0.94
     включает
    -0.93
    那我
    -0.93
    POSITIVE LOGITS
     Compute
    1.52
    compute
    1.34
     compute
    1.30
     tomography
    1.27
     Comput
    1.24
     Computation
    1.23
    ಞ
    1.20
    Compute
    1.17
    计算
    1.16
     计算
    1.15
    Activations Density 0.016%

    No Known Activations