© 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. 74959
    Prev
    Next
    INDEX
    Explanations

    auditory sound and communication

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

    technical content related to sound, audio, acoustics, and hearing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect specific numerical measurement values (e.g., quantitative data points with digits and decimals).

    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
     it
    -1.19
     de
    -1.17
     –
    -1.13
     money
    -1.13
    出了一
    -1.09
     препарат
    -1.04
     dvd
    -1.03
    richText
    -1.03
    してみる
    -1.03
     done
    -1.02
    POSITIVE LOGITS
     Daftar
    1.33
     Sekolah
    1.32
    pięk
    1.29
     THEOREM
    1.28
     desactivar
    1.27
     Aplikasi
    1.27
     дѣ
    1.25
     ἀ
    1.22
    Aplikasi
    1.20
    DAFTAR
    1.20
    Activations Density 0.523%

    No Known Activations