© 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. 34-GEMMASCOPE-RES-131K
    7. 78712
    Prev
    Next
    INDEX
    Explanations

    identifying types and classes

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

    The neuron is strongly activated by the preposition “of.”

    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
    GINIA
    -0.79
    明显
    -0.79
    提供
    -0.79
    ˂
    -0.78
    那些
    -0.78
    angun
    -0.78
    Costs
    -0.77
     нем
    -0.77
    vyš
    -0.77
     miesięcy
    -0.76
    POSITIVE LOGITS
     this
    1.77
     type
    1.41
    这种
    1.22
    type
    1.15
    這種
    1.09
     typu
    1.05
    がこの
    1.04
     этого
    0.98
     either
    0.97
     такого
    0.96
    Activations Density 0.001%

    No Known Activations