© 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. 58422
    Prev
    Next
    INDEX
    Explanations

    related to

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

    The neuron activates on words signaling that one thing is related or connected to another (e.g. “related,” “connected”).

    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
    ᴘ
    -1.62
    
    -1.55
     justifyContent
    -1.54
     autorisation
    -1.46
    zystać
    -1.41
     is
    -1.39
     situe
    -1.38
    graded
    -1.34
    sions
    -1.34
     constate
    -1.34
    POSITIVE LOGITS
     that
    1.70
     inasmuch
    1.49
     henceforth
    1.41
     longstanding
    1.38
     coincident
    1.34
     these
    1.34
     stipul
    1.33
     related
    1.32
    梟
    1.31
     connects
    1.30
    Activations Density 0.080%

    No Known Activations