© 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. 34-GEMMASCOPE-RES-131K
    7. 64071
    Prev
    Next
    INDEX
    Explanations

    open living room plan

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

    The neuron consistently highlights common function words—articles, prepositions, and conjunctions—used to structure and connect phrases in real‐estate property descriptions.

    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
     or
    -1.02
     tucked
    -0.92
     mendengarkan
    -0.85
    Sursa
    -0.84
    鏉
    -0.83
     parked
    -0.81
    ajā
    -0.81
    蒞
    -0.81
     comes
    -0.79
    اقرأ
    -0.79
    POSITIVE LOGITS
     open
    1.98
    Open
    1.67
    open
    1.59
     Open
    1.59
     OPEN
    1.48
     откры
    1.44
     flow
    1.39
     living
    1.34
    OPEN
    1.34
     openness
    1.32
    Activations Density 0.018%

    No Known Activations