© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43913
    Prev
    Next
    INDEX
    Explanations

    radio operator

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

    Neuron 4 finds terms and identifiers related to radio communications (e.g. call signs, amateur-radio operations, public-service events, Morse code, telegraph/key references).

    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
     problemet
    -1.33
     problemen
    -1.23
     топлива
    -1.15
     語
    -1.14
    Your
    -1.13
     your
    -1.13
     mejorar
    -1.13
    最后由
    -1.12
    你想
    -1.05
     даже
    -1.05
    POSITIVE LOGITS
     with
    1.23
    رسد
    1.18
    льники
    1.12
    ).
    1.11
    咽
    1.07
     методом
    1.05
     nab
    1.05
     occasione
    1.05
     tartalomajánló
    1.04
    みたい
    1.02
    Activations Density 0.025%

    No Known Activations