© 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. 22-GEMMASCOPE-RES-131K
    7. 68907
    Prev
    Next
    INDEX
    Explanations

    years old

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

    The neuron strongly activates on descriptions of clothing or fabric tightly hugging or outlining a person’s curves and body shape.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kela
    -1.79
     hina
    -1.77
     DKI
    -1.69
     chré
    -1.66
     teka
    -1.65
     nettoy
    -1.60
     памя
    -1.60
     régl
    -1.55
     conexiones
    -1.55
     melding
    -1.55
    POSITIVE LOGITS
     their
    1.51
     at
    1.38
    ApJ
    1.36
     viena
    1.35
    guint
    1.31
     all
    1.28
    teres
    1.27
     which
    1.26
     on
    1.25
     spørsmål
    1.24
    Activations Density 0.578%

    No Known Activations