© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59148
    Prev
    Next
    INDEX
    Explanations

    signal modulation

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

    The neuron fires on key radio‐frequency transmission and signal processing terms—especially words denoting modulation and demodulation (e.g. AM, QAM, OFDM, carrier, sideband, modulator, demodulator).

    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
     there
    -1.45
     things
    -1.41
    又被
    -1.38
    描いた
    -1.34
    c
    -1.33
    又在
    -1.27
    ㆆ
    -1.27
     segni
    -1.26
    誹
    -1.25
     Varma
    -1.24
    POSITIVE LOGITS
    ،
    1.37
    inige
    1.25
     Dieser
    1.21
    Daftar
    1.20
    idation
    1.18
    \&
    1.18
    Karakteristik
    1.15
    சி
    1.14
     Nicht
    1.13
    διο
    1.13
    Activations Density 0.066%

    No Known Activations