© 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. 951
    Prev
    Next
    INDEX
    Explanations

    loss, loss of, losses

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

    The neuron strongly activates on multi‐digit numeric tokens (e.g. large numbers or measurements).

    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
     Killed
    -0.83
    byn
    -0.76
    oung
    -0.76
    Compre
    -0.73
    Lecturer
    -0.73
    ハッピー
    -0.73
    Rodrigo
    -0.72
     Killing
    -0.71
    Killed
    -0.71
    zné
    -0.69
    POSITIVE LOGITS
     loss
    2.41
     lost
    1.98
    Loss
    1.73
     losses
    1.63
    Lost
    1.57
    loss
    1.55
     lose
    1.55
     LOSS
    1.52
     Loss
    1.52
     Lost
    1.48
    Activations Density 0.079%

    No Known Activations