© 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. 22-GEMMASCOPE-RES-131K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    great, spacious, huge descriptions

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

    The neuron detects mentions of upscale, luxury home features and grand real-estate marketing descriptors.

    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
    🏗
    -1.41
     TikTok
    -1.41
     grâce
    -1.38
    ‏‏
    -1.37
    ĺ
    -1.33
    ₑ
    -1.33
    ⠀⠀
    -1.32
     IoT
    -1.31
    İY
    -1.30
    ́n
    -1.30
    POSITIVE LOGITS
     like
    1.69
     unbelievable
    1.58
     numerous
    1.45
     läßt
    1.45
     not
    1.41
     after
    1.41
     very
    1.39
     great
    1.39
     huge
    1.38
     unusual
    1.38
    Activations Density 0.025%

    No Known Activations