© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25808
    Prev
    Next
    INDEX
    Explanations

    shapes and morphology

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

    The neuron detects words referring to the shape or form of something.

    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
    urrection
    -0.83
    Dennis
    -0.78
     kotlin
    -0.77
    )]$
    -0.76
     Beginnings
    -0.74
     télécharge
    -0.73
     плате
    -0.73
     парфю
    -0.73
     pensando
    -0.72
    Rcpp
    -0.72
    POSITIVE LOGITS
     shape
    6.75
     shapes
    5.25
    shape
    5.13
     Shape
    4.69
    Shape
    4.53
     shaped
    4.13
    SHAPE
    4.00
    shapes
    3.97
    形状
    3.91
     SHAPE
    3.73
    Activations Density 0.224%

    No Known Activations