© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98616
    Prev
    Next
    INDEX
    Explanations

    acoustic ceiling tiles

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

    This neuron fires on words inside page or section titles (e.g. the Title-Cased header lines such as “How Much Are Ceiling Tiles…,” “Fiber Optic Star Ceiling Panel…,” etc.).

    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
     жы
    -0.80
    ⣤
    -0.78
    桃
    -0.73
     verts
    -0.73
    ùa
    -0.73
    )$.
    -0.71
     Situ
    -0.71
     خونه
    -0.68
     electrónica
    -0.67
    ensivo
    -0.67
    POSITIVE LOGITS
     ceiling
    1.98
     Ceiling
    1.66
    Ceiling
    1.60
     ceilings
    1.59
    ceiling
    1.46
     acoustic
    1.21
     panels
    1.18
     tiles
    1.16
    acoustic
    1.13
     suspended
    1.10
    Activations Density 0.015%

    No Known Activations