© 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. 48896
    Prev
    Next
    INDEX
    Explanations

    large forces and sizes

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

    The neuron fires on the key words used in vivid comparisons or similes (e.g. “like,” “the size of,” etc.) that set up figurative imagery.

    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
     weird
    -0.81
     aumento
    -0.79
     sabemos
    -0.76
    oche
    -0.75
     cool
    -0.75
     exciting
    -0.74
     lustre
    -0.74
    兴
    -0.73
     سلام
    -0.73
    êmio
    -0.73
    POSITIVE LOGITS
     nuclear
    1.61
     hurricane
    1.53
     tsunami
    1.52
    tsun
    1.35
     sledge
    1.26
     volcano
    1.25
    nuclear
    1.23
    ricane
    1.23
     earthquake
    1.22
     volcanic
    1.22
    Activations Density 0.095%

    No Known Activations