© 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. 10-GEMMASCOPE-RES-131K
    7. 23875
    Prev
    Next
    INDEX
    Explanations

    display: none

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

    The neuron detects inline or stylesheet-based “hidden” declarations—e.g. CSS rules or attributes (like display:none or class="hidden") that hide elements.

    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
    螃
    -1.92
     corrom
    -1.77
    eſ
    -1.68
    虓
    -1.68
     monstre
    -1.66
    ELECTRIC
    -1.64
     église
    -1.63
     emballage
    -1.61
     photographe
    -1.58
    chees
    -1.55
    POSITIVE LOGITS
    It
    1.94
    in
    1.84
    with
    1.80
    If
    1.78
    what
    1.61
     They
    1.58
     With
    1.57
    All
    1.55
     If
    1.52
    Also
    1.52
    Activations Density 0.009%

    No Known Activations