© 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. 105626
    Prev
    Next
    INDEX
    Explanations

    decompression

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

    the word "decompression" or related forms like "decompress" and "debrief" in technical or medical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on occurrences of the term “decompress” (and its noun form “decompression”).

    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
    </strong>
    -2.20
     It
    -2.13
     startling
    -2.11
     they
    -2.09
     Erfindung
    -2.06
     aveva
    -1.99
     Inhalten
    -1.95
     Veranstal
    -1.95
    ).
    -1.94
     registró
    -1.94
    POSITIVE LOGITS
    ﻒ
    2.03
    <bos>
    1.94
     стоковые
    1.91
    klaim
    1.84
    
    1.80
    🎃
    1.74
    涐
    1.74
     dialed
    1.74
    alucía
    1.73
     dini
    1.73
    Activations Density 0.010%

    No Known Activations