© 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. 22-GEMMASCOPE-RES-131K
    7. 69204
    Prev
    Next
    INDEX
    Explanations

    mobile telephone communication

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

    The neuron selectively fires on occurrences of the word “cellular” (e.g. in “cellular technology” or “cellular telephone”).

    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
     this
    -1.21
     Pagina
    -1.15
     caufe
    -1.15
     setType
    -1.11
     Página
    -1.11
     Industria
    -1.08
    を開始
    -1.06
     Temporada
    -1.05
    </h1>
    -1.03
     grosso
    -1.02
    POSITIVE LOGITS
    LOAT
    1.09
     mobile
    1.08
     Mobile
    1.07
     actualizar
    1.07
    ulink
    1.06
    ượu
    1.05
    բ
    1.05
                           
    1.05
     gibt
    1.04
    bonucleic
    1.04
    Activations Density 0.000%

    No Known Activations