© 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. 10-GEMMASCOPE-RES-131K
    4. 41737
    Prev
    Next
    INDEX
    Explanations

    storage rooms, sheds, and closets

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

    The neuron fires on words naming physical sub-areas, rooms, utility or equipment spaces (e.g. “shed,” “tack room,” “engine room,” “storage area,” “telecommunications closet,” 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_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
    ientemente
    -1.08
    renewcommand
    -1.06
     rengi
    -1.05
    ⅱ
    -1.04
    apparition
    -1.02
    jshint
    -1.02
    Río
    -1.02
     any
    -1.02
     nahezu
    -1.01
    Jum
    -1.00
    POSITIVE LOGITS
     but
    1.26
     vigencia
    1.24
     pidana
    1.23
    licted
    1.22
     warum
    1.19
    臾
    1.16
    しないで
    1.15
     said
    1.15
     until
    1.13
     needed
    1.10
    Activations Density 0.066%

    No Known Activations