© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115547
    Prev
    Next
    INDEX
    Explanations

    lined or lining

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

    This neuron strongly activates on very common function words (high-frequency stop words like “and,” “of,” “on,” “or,” “to,” “in,” “the,” etc.).

    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
     iterative
    -0.75
    }^{+\
    -0.71
     Bolton
    -0.68
    団
    -0.67
    jab
    -0.66
     concentrated
    -0.66
    享
    -0.66
    ≐
    -0.65
    íram
    -0.65
     Firth
    -0.65
    POSITIVE LOGITS
     lining
    4.41
     lined
    4.34
    lined
    3.56
     Lining
    3.52
     Lined
    3.36
    lining
    3.16
     linings
    3.13
     liners
    2.38
     liner
    2.31
    liner
    1.84
    Activations Density 0.071%

    No Known Activations