© 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. 10-GEMMASCOPE-RES-131K
    7. 113270
    Prev
    Next
    INDEX
    Explanations

    framed objects and figurative framing

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

    The neuron fires on mentions of “framed” or its variants (e.g. “unframed,” “framing”) indicating when something is described as framed.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    應該
    -2.34
     ด้วย
    -2.27
    ↵
    -2.27
     chilena
    -2.25
    
    -2.23
    趵
    -2.20
     porque
    -2.17
     pero
    -2.16
     ſou
    -2.11
    
    -2.09
    POSITIVE LOGITS
     vorigen
    2.81
     Allgemeinen
    2.50
     kostenlosen
    2.44
     dritten
    2.41
    蚡
    2.36
    ໊
    2.33
    沨
    2.27
    –
    2.23
    蠵
    2.23
    fillment
    2.19
    Activations Density 0.004%

    No Known Activations